Francis Bach - INRIA - ENS

Francis Bach

INRIA - SIERRA project-team
Departement d'Informatique de l'Ecole Normale Superieure

PSL Research University
Centre de Recherche INRIA de Paris
48 rue Barrault

CS61534

75647 Paris Cedex

Blog - Tutorials - Courses - Students - Alumni - Publications - Software

Book: Learning Theory from First Principles, published in December 2024 at MIT Press

Final pdf version
Code (python, Matlab)
Blog post

I am a researcher at INRIA, leading since 2011 the SIERRA project-team, which is part of the Computer Science Department at Ecole Normale Supérieure, and a joint team between CNRS, ENS, and INRIA. I completed my Ph.D. in Computer Science at U.C. Berkeley, working with Professor Michael Jordan, and spent two years in the Mathematical Morphology group at Ecole des Mines de Paris, I then joined the WILLOW project-team at INRIA/Ecole Normale Supérieure/CNRS from 2007 to 2010. From 2009 to 2014, I was running the ERC project SIERRA, and I am now running the ERC project SEQUOIA. I was elected in 2020 to the French Academy of Sciences. I am interested in statistical machine learning, and especially in optimization, sparse methods, kernel-based learning, neural networks, graphical models, and signal processing. [CV (English)] [CV (French)] [short bio][short bio (francais)]

Tutorials / mini-courses / keynotes (recent - older ones below)

February 2026: CUSO Winter school, Les Diablerets [notes] [board-1] [board-2] [board-3]
December 2025: International Conference on Statistics and Data Science (ICSDS) [slides]

July 2025: Conference on Learning Theory [slides]
April 2025: Graduate School in Systems, Optimization, Control and Networks (SOCN) [board-1] [board-2] [board-3] [board-4] [board-5] [board-6] [exercises]
September 2024: CIME School on High-Dimensional Approximation [notes]
September 2023: Summer school on distributed learning [slides]

July 2021: PRAIRIE/MIAI AI summer school [slides]
September 2020: Hausdorff School, MCMC: Recent developments and new connections - Large-scale machine learning and convex optimization [slides]
June 2020: Machine Learning Summer School, Tubingen - Large-scale machine learning and convex optimization [slides]

Courses (recent - older ones below)

Fall 2026: Learning theory from first principles - Mastere M2 IASD
Fall 2025: Learning theory from first principles - Mastere M2 IASD
Fall 2024: Learning theory from first principles - Mastere M2 IASD
Fall 2023: Learning theory from first principles - Mastere M2 Mash
Fall 2022: Learning theory from first principles - Mastere M2 Mash
Spring 2022: Optimisation et Apprentissage Statistique - Master M2 "Mathematiques de l'aleatoire" - Universite Paris-Sud (Orsay)
Fall 2021: Learning theory from first principles - Mastere M2 Mash
Spring 2021: Statistical machine learning - Ecole Normale Superieure (Paris)
Spring 2021: Machine Learning - Masters ICFP, Ecole Normale Superieure
Spring 2021: Optimisation et Apprentissage Statistique - Master M2 "Mathematiques de l'aleatoire" - Universite Paris-Sud (Orsay)

PhD Students and Postdocs

Eliot Beyler
Eugène Berta, co-advised with Michael Jordan
Nabil Boukir, co-advised with Michael Jordan
Sacha Braun, co-advised with Michael Jordan
Léo Dana, co-advised with Loucas Pillaud-Vivien
Juliette Decugis, co-advised with Gabriel Synnaeve and Taco Cohen
Etienne Gauthier, co-advised with Michael Jordan
Armand Gissler
Frederik Kunstner
Lucas Levy, co-advised with Michael Jordan
Simon Martin, co-advised with Giulio Biroli
Adam Perbost, co-advised with Pierre Marion
Aditya Varre, co-advised with Pierre Marion

Alumni

Martin Arjovsky, Research scientist, Deepmind

Dmitry Babichev, Researcher, Huawei

P Balamurugan, Assistant Professor, Indian Institute of Technology, Bombay
Anaël Beaugnon, Data scientist, Roche

Amit Bermanis, Senior Algorithms Researcher, ThetaRay
Eloïse Berthier, Researcher at ENSTA, Paris
Raphaël Berthier, tenure-track research faculty, Inria Sorbonne Université
Alberto Bietti, Research scientist, Flat Iron Institute, New York
Bertille Brossollet (Follain), Agregio Solution
Vivien Cabannes, Research Scientist, Meta, Paris
Lénaïc Chizat, Assistant Professor, EPFL, Ecole Polytechnique Fédérale de Lausanne

Timothee Cour, Engineer at Google
Hadi Daneshmand, Assistant professor, University of Virginia
Alexandre Défossez, Research scientist, Kyutai, Paris
Aymeric Dieuleveut, Professor, Ecole Polytechnique, Palaiseau

Christophe Dupuy, Amazon, Cambridge, USA

Pascal Germain, Assistant professor, Université Laval, Canada
Robert Gower, Research Scientist, Flatiron Institute, New York

Edouard Grave, Research scientist, Kyutai, Paris

Zaid Harchaoui, Associate Professor, University of Washington
Hadrien Hendrikx, Researcher, Inria Grenoble

Toby Hocking, Assistant Professor, Northern Arizona University
David Holzmüller, Researcher, Inria, Saclay

Nicolas Flammarion, Assistant Professor, Ecole Polytechnique Federale de Lausanne

Fajwel Fogel, Research scientist, Sancare
Rodolphe Jenatton, CTO, Bioptimus
Armand Joulin, Research scientist, Google Deepmind, Paris
Hans Kersting, Research Scientist, Yahoo Research
Ziad Kobeissi, Researcher, Inria, Saclay
Sesh Kumar, Research fellow, Imperial College Business School
Simon Lacoste-Julien, Professor, Université de Montréal

Remi Lajugie, Professeur d'Informatique, Lycée Janson de Sailly, Paris
Marc Lambert, Research engineer, DGA

Augustin Lefèvre, Data scientist, YKems
Ivan Lerner, Praticien Hospitalo-Universitaire, Université Paris-Cité
Nicolas Le Roux, Researcher, Microsoft Research, Montréal

Ronny Luss, Researcher, IBM Research
Julien Mairal, Researcher at Inria, Grenoble
Ulysse Marteau-Ferey, Research scientist, Owkin

Bamdev Mishra, Research scientist, Amazon Bangalore
Céline Moucer, Ministère du Budget
Boris Muzellec, Research scientist, Owkin
Anil Nelakanti, Research scientist, Amazon Bangalore
Alex Nowak-Vila, Research scientist, Owkin
Guillaume Obozinski, Deputy Chief Data Scientist, Swiss Data Science Center
Dmitrii Ostrovskii, Postdoctoral researcher, University of South California
Loucas Pillaud-Vivien, Postdoctoral researcher, Ecole Polytechnique Federale de Lausanne
Anastasia Podosinnikova, Postdoctoral fellow, MIT
Fabian Pedregosa, Researcher, Google Brain, Montréal

Rafael Rezende, Postdoctoral researcher, Naver Labs, Grenoble
Anant Raj, Assistant Professor, Indian Institute of Science, Bangalore, India
Théo Ryffel, Arkhn

Thomas Schatz, Assistant professor, Aix-Marseille Université, Marseille
Corbinian Schlosser
Fabian Schaipp, Research Scientist, Cohere
Mark Schmidt, Associate professor, University of British Columbia

Damien Scieur, Research scientist, Samsung, Montreal

Nino Shervashidze, Data scientist, Sancare
Tatiana Shpakova, Researcher, Huawei

Matthieu Solnon, Professeur de Mathématiques, CPGE, Lycée Lavoisier
Lawrence Stewart, Research scientist, Google Deepmind, Paris
Adrien Taylor, Research scientist, Inria Paris
Blake Woodworth, Assistant Professor, George Washington University
Mikhail Zaslavskiy, Byopt

Publications

2026

Eloïse Berthier, Ziad Kobeissi, Francis Bach. A Stochastic Optimization Approach to Control-Affine Optimal Control Problems. Technical report, arXiv:2609.29265, 2026. [pdf]

Liviu Aolaritei, Lucas Lévy, Francis Bach, Michael I. Jordan. Beyond Optimal Rates in Stochastic Optimization: Trajectory-Adaptive Stopping Rules. Technical report, arXiv:2608.25551, 2026. [pdf]

Francis Bach. Regularized Variational and Spectral Log-Density-Ratio Estimation in the Gaussian Location Model. Technical report, arXiv:2607.01895, 2026. [pdf]

Juliette Decugis, Sean O'Brien, Francis Bach, Gabriel Synnaeve, Taco Cohen. Don’t Let Gains FADE: Breaking Down Policy Gradient Weights in RL. Technical report, arXiv:2607.01490, 2026. [pdf]

Juliette Decugis, Fabian Gloeckle, Francis Bach, Taco Cohen, Gabriel Synnaeve. DecompRL: Solving Harder Problems by Learning Modular Code Generation. Technical report, arXiv:2607.02390, 2026. [pdf]

Eugène Berta, David Holzmüller, Francis Bach, Michael I. Jordan. CalArena: A Large-Scale Post-Hoc Calibration Benchmark. Technical report, arXiv:2605.30188, 2026. [pdf]

David Vävinggren, Francis Bach, André M. H. Teixeira, Dave Zachariah, Antônio H. Ribeiro. A Robust Optimization Approach to Sparse Principal Component Analysis. Technical report, arXiv:2606.03553, 2026. [pdf]

Francis Bach. A Spectral Framework for Closed-Form Relative Density Estimation. Technical report, arXiv:2605.10668, 2026. [pdf] [code] [slides]

Sacha Braun, Michael I. Jordan, Francis Bach. Super-Level-Set Regression: Conditional Quantiles via Volume Minimization. Technical report, arXiv:2605.06210, 2026. [pdf]

Etienne Gauthier, Francis Bach, Michael I. Jordan. Explaining and Preventing Alignment Collapse in Iterative RLHF. Technical report, arXiv:2605.04266, 2026. [pdf]

Eugène Berta, Sacha Braun, David Holzmüller, Francis Bach, Michael I. Jordan. A Variational Estimator for L_p Calibration Errors. Technical report, arXiv:2602.24230, 2026. [pdf]

Sacchit Kale, Piyushi Manupriya, Pierre Marion, Francis Bach, Anant Raj. Stretched Exponential Convergence of (Stochastic) Gradient Descent for Separable Logistic Regression. Transactions of Machine Learning Research, 2026. [pdf]

Armand Gissler, Saeed Saremi, Francis Bach. Adjusted Scores for Discrete Langevin Algorithms. Technical report, arXiv:2602.15587, 2026. [pdf]

Benjamin Dubois-Taine, Laurent Pfeiffer, Nadia Oudjane, Adrien Seguret, Francis Bach. Two-stage stochastic algorithm for solving large-scale (non)-convex separable optimization problems under affine constraints. Technical report, arXiv:2602.06637, 2026. [pdf]

Simon Martin, Giulio Biroli, Francis Bach. High-Dimensional Analysis of Gradient Flow for Extensive-Width Quadratic Neural Networks. Journal of Machine Learning Research, 27(136):1−182, 2026, 2026. [pdf]

Etienne Gauthier, Francis Bach, Michael I. Jordan. Betting on Equilibrium: Monitoring Strategic Behavior in Multi-Agent Systems. Technical report, arXiv:2601.05427, 2026. [pdf]

Eugène Berta, David Holzmüller, Michael I. Jordan, Francis Bach. Structured Matrix Scaling for Multi-Class Calibration. Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS), 2026. [pdf]

Etienne Gauthier, Francis Bach, Michael I. Jordan. Adaptive Coverage Policies in Conformal Prediction. Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS), 2026. [pdf]

Lawrence Stewart, Francis Bach, Quentin Berthet. Beyond Binning: Soft Task Reformulation for Deep Regression. Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS), 2026. [pdf]

Francis Bach. On the Effectiveness of the z-Transform Method in Quadratic Optimization. Journal of Machine Learning Research, 27(180):1−43, 2026. [pdf]

2025

Francis Bach. A Convex Loss Function for Set Prediction with Optimal Trade-offs Between Size and Conditional Coverage. Technical report, arXiv:2512.19142, 2025. [pdf]

Sacha Braun, David Holzmüller, Michael I. Jordan, Francis Bach. Conditional Coverage Diagnostics for Conformal Prediction. Technical report, arXiv:2512.11779, 2025. [pdf]

Antônio H. Ribeiro, David Vävinggren, Dave Zachariah, Thomas B. Schön, Francis Bach. Kernel Learning with Adversarial Features: Numerical Efficiency and Adaptive Regularization. Advances in Neural Information Processing Systems (NeurIPS), 2025. [pdf]

Léo Dana, Francis Bach, Loucas Pillaud-Vivien. Convergence of Shallow ReLU Networks on Weakly Interacting Data. Advances in Neural Information Processing Systems (NeurIPS), 2025. [pdf]

Frederik Kunstner, Francis Bach. Scaling Laws for Gradient Descent and Sign Descent for Linear Bigram Models under Zipf’s Law. Advances in Neural Information Processing Systems (NeurIPS), 2025. [pdf]

Etienne Gauthier, Francis Bach, Michael I. Jordan. Backward Conformal Prediction. Advances in Neural Information Processing Systems (NeurIPS), 2025. [pdf]

Nathan Doumèche, Francis Bach, Gérard Biau, Claire Boyer. Fast kernel methods: Sobolev, physics-informed, and additive models. Technical report, arXiv:2509.02649, 2025. [pdf]

Eliot Beyler, Francis Bach. Convergence of Deterministic and Stochastic Diffusion-Model Samplers: A Simple Analysis in Wasserstein Distance. Technical report, arXiv:2508.03210, 2025. [pdf]

Sacha Braun, Eugène Berta, Michael I. Jordan, Francis Bach. Multivariate Conformal Prediction via Conformalized Gaussian Scoring. Technical report, arXiv:2507.20941, 2025. [pdf]

Zijian Guo, Zhenyu Wang, Yifan Hu, Francis Bach. Statistical Inference for Conditional Group Distributionally Robust Optimization with Cross-Entropy Loss. Technical report, arXiv:2507.09905, 2025. [pdf]

Zhenyu Wang, Molei Liu, Jing Lei, Francis Bach, Zijian Guo. StablePCA: Learning Shared Representations across Multiple Sources via Minimax Optimization. Technical report, arXiv:2505.00940, 2025. [pdf]

Marc Lambert, Francis Bach, Silvère Bonnabel. Entropy Regularized Variational Dynamic Programming for Stochastic Optimal Control. Technical report, HAL:05016406, 2025. [pdf]

Sacha Braun, Liviu Aolaritei, Michael I. Jordan, Francis Bach. Minimum Volume Conformal Sets for Multivariate Regression. Technical report, arXiv:2503.19068, 2025. [pdf]

Etienne Gauthier, Francis Bach, Michael I. Jordan. E-Values Expand the Scope of Conformal Prediction. Technical report, arXiv:2503.13050, 2025. [pdf]

Nathan Doumèche, Francis Bach, Éloi Bedek, Gérard Biau, Claire Boyer, Yannig Goude. Forecasting time series with constraints. Technical report, arXiv:2502.10485, 2025. [pdf]

Eugène Berta, David Holzmüller, Michael I. Jordan, Francis Bach. Rethinking Early Stopping: Refine, Then Calibrate. Technical report, arXiv:2501.19195, 2025. [pdf] [slides]

Eliot Beyler, Francis Bach. Optimal Denoising in Score-Based Generative Models: The Role of Data Regularity. Journal of Machine Learning Research, 26:1-48, 2025. [pdf]

David Holzmüller, Francis Bach. Convergence Rates for Non-log-concave Sampling and Log-partition Estimation. Journal of Machine Learning Research, 26(249):1−72, 2025. [pdf]

Alexandre François, Antonio Orvieto, Francis Bach. An Uncertainty Principle for Linear Recurrent Neural Networks. Proceedings of the Conference on Learning Theory (COLT), 2025. [pdf]

Francis Bach, Saeed Saremi. Sampling Binary Data by Denoising through Score Functions. Proceedings of the International Conference on Machine Learning (ICML), 2025. [pdf]

Fabian Schaipp, Alexander Hägele, Adrien Taylor, Umut Simsekli, Francis Bach. The Surprising Agreement Between Convex Optimization Theory and Learning-Rate Scheduling for Large Model Training. Proceedings of the International Conference on Machine Learning (ICML), 2025. [pdf]

Etienne Gauthier, Francis Bach, Michael I. Jordan. Statistical Collusion by Collectives on Learning Platforms. Proceedings of the International Conference on Machine Learning (ICML), 2025. [pdf]

Sebastian G. Gruber, Francis Bach. Optimizing Estimators of Squared Calibration Errors in Classification. Transactions of Machine Learning Research, 2025. [pdf]

Eliot Beyler, Francis Bach. Variational Inference on the Boolean Hypercube with the Quantum Entropy. Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS), 2025. [pdf]

Antônio H. Ribeiro, Thomas B. Schön, Dave Zachariah, Francis Bach. Efficient Optimization Algorithms for Linear Adversarial Training. Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS), 2025. [pdf]

Alessandro Rudi, Ulysse Marteau-Ferey, Francis Bach. Finding Global Minima via Kernel Approximations. Mathematical Programming, 209(1):703-784, 2025. [pdf]

Nathan Doumèche, Francis Bach, Gérard Biau, Claire Boyer. Physics-informed kernel learning. Journal of Machine Learning Research, 26(124):1−39, 2025. [pdf]

Bertille Follain, Francis Bach. Enhanced Feature Learning via Regularisation: Integrating Neural Networks and Kernel Methods. Journal of Machine Learning Research, 26(172):1-56, 2025. [pdf]

C. Moucer, A. Taylor, F. Bach. Geometry-dependent matching pursuit: a transition phase for convergence on linear regression and LASSO. Journal of Machine Learning Research, 26(299):1-50, 2025. [pdf]

2024

C. Moucer, A. Taylor, F. Bach. Constructive approaches to concentration inequalities with independent random variables. Technical report, arXiv:2408.16480, 2024. [pdf]

C. Chazal, A. Korba, F. Bach. Statistical and Geometrical properties of regularized Kernel Kullback-Leibler divergence. Advances in Neural Information Processing Systems (NeurIPS), 2024. [pdf]

S. Bonnabel, M. Lambert, F. Bach. Low-rank plus diagonal approximations for Riccati-like matrix differential equations. SIAM Journal on Matrix Analysis and Applications, 45(3):1669-1688, 2024. [pdf]

M. Lambert, S. Bonnabel, F. Bach. Variational Dynamic Programming for Stochastic Optimal Control. Conference on Decision and Control, 2024. [pdf]

N. Doumèche, F. Bach, G. Biau, C. Boyer. Physics-informed machine learning as a kernel method. Proceedings of the Conference on Learning Theory (COLT), 2024. [pdf]

E. Berta, F. Bach, M. I. Jordan. Classifier Calibration with ROC-Regularized Isotonic Regression. Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS), 2024. [pdf]

S. Martin, F. Bach, G. Biroli. On the Impact of Overparameterization on the Training of a Shallow Neural Network in High Dimensions. Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS), 2024. [pdf]

V. Cabannes, F. Bach. The Galerkin method beats Graph-Based Approaches for Spectral Algorithms. Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS), 2024. [pdf] [code]

S. Saremi, J.-W. Park, F. Bach. Chain of Log-Concave Markov Chains. Proceedings of the International Conference on Learning Representations (ICLR), 2024. [pdf] [slides]

U. Marteau-Ferey, F. Bach, A. Rudi. Second Order Conditions to Decompose Smooth Functions as Sums of Squares. SIAM Journal on Optimization, 34:616-641, 2024. [pdf]

F. Bach. High-dimensional analysis of double descent for linear regression with random projections. SIAM Journal on Mathematics of Data Science, 6(1):26-50, 2024. [pdf]

F. Bach. Sum-of-squares relaxations for information theory and variational inference. Foundations of Computational Mathematics, 2024. [pdf]

F. Bach. Sum-of-squares relaxations for polynomial min-max problems over simple sets. Mathematical Programming, 2024. [pdf]

A. Vacher, B. Muzellec, F. Bach, F.-X. Vialard, A. Rudi. Optimal Estimation of Smooth Transport Maps with Kernel SoS. SIAM Journal on Mathematics of Data Science, 6(2):311-342, 2024. [pdf]

B. Follain, F. Bach. Nonparametric Linear Feature Learning in Regression Through Regularisation. Electronic Journal of Statistics, 18(2):4075-4118. [pdf]

2023

A. Joudaki, H. Daneshmand, F. Bach. On the impact of activation and normalization in obtaining isometric embeddings at initialization. Advances in Neural Information Processing Systems (NeurIPS), 2023. [pdf]

L. Stewart, F. Bach, F. Llinares-López, Q. Berthet. Differentiable Clustering with Perturbed Spanning Forests. Advances in Neural Information Processing Systems (NeurIPS), 2023. [pdf] [code]

A. H. Ribeiro, D. Zachariah, F. Bach, T. B. Schön. Regularization properties of adversarially-trained linear regression. Advances in Neural Information Processing Systems (NeurIPS), 2023. [pdf]

S. Saremi, R. K. Srivastava, F. Bach. Universal Smoothed Score Functions for Generative Modeling. Technical report, arXiv:2303.11669, 2023. [pdf]

B. Tzen, A. Raj, M. Raginsky, F. Bach. Variational principles for mirror descent and mirror Langevin dynamics. IEEE Control Systems Letters, 7:1542-1547, 2023. [pdf]

L. Pillaud-Vivien, F. Bach. Kernelized diffusion maps. Proceedings of the Conference on Learning Theory (COLT), 2023. [pdf]

B. Woodworth, K. Mishchenko, F. Bach. Two losses are better than one: Faster optimization using a cheaper proxy. Proceedings of the International Conference on Machine Learning (ICML), 2023. [pdf]

F. Bach. On the relationship between multivariate splines and infinitely-wide neural networks. Technical report, arXiv:2302.03459, 2023. [pdf]

F. Bach. Information theory with kernel methods. IEEE Transactions in Information Theory, 69(2):752-775, 2023. [pdf]

F. Bach, A. Rudi. Exponential convergence of sum-of-squares hierarchies for trigonometric polynomials. SIAM Journal on Optimization, 33(3): 2137-2159. [pdf]

L. Stewart, F. Bach, Q. Berthet, J.-P. Vert. Regression as classification: Influence of task formulation on neural network features. Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS), 2023. [pdf]

A. Orvieto, A. Raj, H. Kersting, F. Bach. Explicit regularization in overparametrized models via noise injection. Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS), 2023. [pdf]

C. Moucer, A. Taylor, F. Bach. A systematic approach to Lyapunov analyses of continuous-time models in convex optimization. SIAM Journal on Optimization, 33(3):1558-1586, 2023. [pdf]

M. Lambert, S. Bonnabel, F. Bach. The limited-memory recursive variational Gaussian approximation (L-RVGA). Statistics and Computing, 33, 2023. [pdf]

2022

A. Défossez, L. Bottou, F. Bach, N. Usunier. A Simple convergence proof of Adam and Adagrad. Transactions on Machine Learning Research, 2022. [pdf]

A. Lucchi, F. Proske, A. Orvieto, F. Bach, H. Kersting. On the Theoretical Properties of Noise Correlation in Stochastic Optimization. Advances in Neural Information Processing Systems (NeurIPS), 2022. [pdf]

K. Mishchenko, F. Bach, M. Even, B. Woodworth. Asynchronous SGD Beats Minibatch SGD Under Arbitrary Delays. Advances in Neural Information Processing Systems (NeurIPS), 2022. [pdf]

M. Lambert, S. Chewi, F. Bach, S. Bonnabel, P. Rigollet. Variational inference via Wasserstein gradient flows. Advances in Neural Information Processing Systems (NeurIPS), 2022. [pdf]

B. Dubois-Taine, F. Bach, Q. Berthet, A. Taylor. Fast Stochastic Composite Minimization and an Accelerated Frank-Wolfe Algorithm under Parallelization. Advances in Neural Information Processing Systems (NeurIPS), 2022. [pdf]

V. Cabannes, F. Bach, V. Perchet, A. Rudi. Active Labeling: Streaming Stochastic Gradients. Advances in Neural Information Processing Systems (NeurIPS), 2022. [pdf]

E. Berthier, Z. Kobeissi, F. Bach. A Non-asymptotic Analysis of Non-parametric Temporal-Difference Learning. Advances in Neural Information Processing Systems (NeurIPS), 2022. [pdf]

A. Joudaki, H. Daneshmand, F. Bach. Entropy Maximization with Depth: A Variational Principle for Random Neural Networks. Technical report, arXiv:2205.13076, 2022. [pdf]

H. Daneshmand, F. Bach. Polynomial-time sparse measure recovery. Technical report, arXiv:2204.07879, 2022. [pdf]

Z. Kobeissi, F. Bach. On a Variance Reduction Correction of the Temporal Difference for Policy Evaluation in the Stochastic Continuous Setting. Technical report, arXiv:2202.07960, 2022. [pdf]

A. Orvieto, H. Kersting, F. Proske, F. Bach, A. Lucchi. Anticorrelated Noise Injection for Improved Generalization. Proceedings of the International Conference on Machine Learning (ICML), 2022. [pdf]

T. Ryffel, F. Bach, D. Pointcheval. Differential Privacy Guarantees for Stochastic Gradient Langevin Dynamics. Technical report, arXiv:2201.11980, 2022. [pdf]

M. Lambert, S. Bonnabel, F. Bach. The continuous-discrete variational Kalman filter (CD-VKF). IEEE Conference on Decision and Control, 2022. [pdf]

E. Berthier, J. Carpentier, A. Rudi, F. Bach. Infinite-Dimensional Sums-of-Squares for Optimal Control. IEEE Conference on Decision and Control, 2022. [pdf]

B. Woodworth, F. Bach, A. Rudi. Non-Convex Optimization with Certificates and Fast Rates Through Kernel Sums of Squares. Proceedings of the Conference on Learning Theory (COLT), 2022. [pdf]

A. Raj, F. Bach. Convergence of uncertainty sampling for active learning. Proceedings of the International Conference on Machine Learning (ICML), 2022. [pdf]

F. Bach, L. Chizat. Gradient Descent on Infinitely Wide Neural Networks: Global Convergence and Generalization. Proceedings of the International Congress of Mathematicians, 2022. [pdf]

Y. Sun, F. Bach. Screening for a Reweighted Penalized Conditional Gradient Method. Open Journal of Mathematical Optimization, 3:1-35, 2022 [pdf]

M. Barré, A. Taylor, F. Bach. A note on approximate accelerated forward-backward methods with absolute and relative errors, and possibly strongly convex objectives. Open Journal of Mathematical Optimization, 3(1), 2022. [pdf]

U. Marteau-Ferey, A. Rudi, F. Bach. Sampling from Arbitrary Functions via PSD Models. Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS), 2022. [pdf]

A. Nowak-Vila, A. Rudi, F. Bach. On the Consistency of Max-Margin Losses. Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS), 2022. [pdf]

M. Lambert, S. Bonnabel, F. Bach. The recursive variational Gaussian approximation (R-VGA). Statistics and Computing, 32(1), 2022. [pdf]

2021

B. Muzellec, F. Bach, A. Rudi. Learning PSD-valued functions using kernel sums-of-squares. Technical report, arXiv:2111.11306, 2021. [pdf]

B. Muzellec, F. Bach, A. Rudi. A Note on Optimizing Distributions using Kernel Mean Embeddings. Technical report, arXiv:2106.09994, 2021. [pdf]

V. Cabannes, L. Pillaud-Vivien, F. Bach, A. Rudi. Overcoming the curse of dimensionality with Laplacian regularization in semi-supervised learning. Advances in Neural Information Processing Systems (NeurIPS), 2021. [pdf]

H. Daneshmand, A. Joudaki, F. Bach. Batch Normalization Orthogonalizes Representations in Deep Random Networks. Advances in Neural Information Processing Systems (NeurIPS), 2021. [pdf]

M. Even, R. Berthier, F. Bach, N. Flammarion, P. Gaillard, H. Hendrikx, L. Massoulié, A. Taylor. A Continuized View on Nesterov Acceleration for Stochastic Gradient Descent and Randomized Gossip. Advances in Neural Information Processing Systems (NeurIPS), 2021. [pdf]

F. Bach. On the Effectiveness of Richardson Extrapolation in Data Science. SIAM Journal on Mathematics of Data Science, 3(4):1251-1277, 2021. [pdf] [slides]

A. Vacher, B. Muzellec, A. Rudi, F. Bach, F.-X. Vialard. A Dimension-free Computational Upper-bound for Smooth Optimal Transport Estimation. Proceedings of the Conference on Learning Theory (COLT), 2021. [pdf]

V. Cabannes, F. Bach, A. Rudi. Fast rates in structured prediction. Proceedings of the Conference on Learning Theory (COLT), 2021. [pdf]

V. Cabannes, F. Bach, A. Rudi. Disambiguation of weak supervision with exponential convergence rates. Proceedings of the International Conference on Machine Learning (ICML), 2021. [pdf]

A. Bietti, F. Bach. Deep Equals Shallow for ReLU Networks in Kernel Regimes. Proceedings of the International Conference on Learning Representations (ICLR), 2021. [pdf]

A. Raj, F. Bach. Explicit Regularization of Stochastic Gradient Methods through Duality. Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS), 2021. [pdf]

D. Ostrovskii, F. Bach. Finite-sample Analysis of M-estimators using Self-concordance. Electronic Journal of Statistics, 15(1):326-391, 2021. [pdf]

E. Berthier, J. Carpentier, F. Bach. Fast and Robust Stability Region Estimation for Nonlinear Dynamical Systems. Proceedings of the European Control Conference (ECC), 2021. [pdf]

R. M. Gower, P. Richtárik, F. Bach. Stochastic Quasi-Gradient Methods: Variance Reduction via Jacobian Sketching. Mathematical Programming, 188:135–192, 2021. [pdf]

2020

U. Marteau-Ferey, F. Bach, A. Rudi. Non-parametric Models for Non-negative Functions. Advances in Neural Information Processing Systems (NeurIPS), 2020. [pdf]

H. Hendrikx, F. Bach, L. Massoulié. Dual-Free Stochastic Decentralized Optimization with Variance Reduction. Advances in Neural Information Processing Systems (NeurIPS), 2020. [pdf]

R. Berthier, F. Bach, P. Gaillard. Tight Nonparametric Convergence Rates for Stochastic Gradient Descent under the Noiseless Linear Model. Advances in Neural Information Processing Systems (NeurIPS), 2020. [pdf]

Q. Berthet, M. Blondel, O. Teboul, M. Cuturi, J.-P. Vert, F. Bach. Learning with Differentiable Perturbed Optimizers. Advances in Neural Information Processing Systems (NeurIPS), 2020. [pdf] [video]

H. Daneshmand, J. Kohler, F. Bach, T. Hofmann, A. Lucchi. Batch Normalization Provably Avoids Rank Collapse for Randomly Initialised Deep Networks. Advances in Neural Information Processing Systems (NeurIPS), 2020. [pdf]

M. Barré, A. Taylor, F. Bach. Principled Analyses and Design of First-Order Methods with Inexact Proximal Operators. Technical report, arXiv:2006.06041, 2020. [pdf]

T. Eboli, A. Nowak-Vila, J. Sun, F. Bach, J. Ponce, A. Rudi. Structured and Localized Image Restoration. Technical report, arXiv:2006.09261, 2020. [pdf]

T. Ryffel, D. Pointcheval, F. Bach. ARIANN: Low-Interaction Privacy-Preserving Deep Learning via Function Secret Sharing. Technical report, arXiv:2006.04593, 2020. [pdf]

H. Hendrikx, F. Bach, L. Massoulié. An Optimal Algorithm for Decentralized Finite Sum Optimization. Technical report, arXiv:2005.10675, 2020. [pdf]

R. Sankaran, F. Bach, C. Bhattacharyya. Learning With Subquadratic Regularization : A Primal-Dual Approach. Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI), 2020. [pdf]

A. Nowak-Vila, F. Bach, A. Rudi. Consistent Structured Prediction with Max-Min Margin Markov Networks. Proceedings of the International Conference on Machine Learning (ICML), 2020. [pdf]

V. Cabannes, A. Rudi, F. Bach. Structured Prediction with Partial Labelling through the Infimum Loss. Proceedings of the International Conference on Machine Learning (ICML), 2020. [pdf]

H. Hendrikx, L. Xiao, S. Bubeck, F. Bach, L. Massoulié. Statistically Preconditioned Accelerated Gradient Method for Distributed Optimization. Proceedings of the International Conference on Machine Learning (ICML), 2020. [pdf] [video]

M. Ballu, Q. Berthet, F. Bach. Stochastic Optimization for Regularized Wasserstein Estimators. Proceedings of the International Conference on Machine Learning (ICML), 2020. [pdf]

Y. Sun, F. Bach. Safe Screening for the Generalized Conditional Gradient Method. Technical report, arXiv:2002.09718, 2020. [pdf]

L. Chizat, F. Bach. Implicit Bias of Gradient Descent for Wide Two-layer Neural Networks Trained with the Logistic Loss. Proceedings of the Conference on Learning Theory (COLT) [pdf] [video] [slides]

E. Berthier, F. Bach. Max-Plus Linear Approximations for Deterministic Continuous-State Markov Decision Processes. IEEE Control Systems Letters, 4(3):767-772, 2020. [pdf]

L. Pillaud-Vivien, F. Bach, T. Lelièvre, A. Rudi, G. Stoltz. Statistical Estimation of the Poincaré constant and Application to Sampling Multimodal Distributions. Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS), 2020. [pdf]

R. Berthier, F. Bach, P. Gaillard. Accelerated Gossip in Networks of Given Dimension using Jacobi Polynomial Iterations. SIAM Journal on Mathematics of Data Science 2(1):24-47, 2020. [pdf]

D. Scieur, A. d'Aspremont, F. Bach. Regularized Nonlinear Acceleration. Mathematical Programming, 179:47-83, 2020. [pdf]

R. M. Gower, M. Schmidt, F. Bach. P. Richtárik. Variance-Reduced Methods for Machine Learning. Proceedings of the IEEE, 108(11):1968-1983, 2020. [pdf]

A. Dieuleveut, A. Durmus, F. Bach. Bridging the Gap between Constant Step Size Stochastic Gradient Descent and Markov Chains. Annals of Statistics, 48(3):1348-1382, 2020. [pdf]

2019

P. Askenazy, F. Bach. IA et emploi : Une menace artificielle. Pouvoirs, 170, 33-41, 2019. [pdf]

K. Scaman, F. Bach, S. Bubeck, Y.-T. Lee, L. Massoulié. Optimal Convergence Rates for Convex Distributed Optimization in Networks. Journal of Machine Learning Research, 20(159):1-31, 2019. [pdf]

U. Marteau-Ferey, F. Bach, A. Rudi. Globally convergent Newton methods for ill-conditioned generalized self-concordant Losses. Advances in Neural Information Processing Systems (NeurIPS), 2019. [pdf] [supplement] [slides] [poster]

H. Hendrikx, F. Bach, L. Massoulié. An accelerated decentralized stochastic proximal algorithm for finite Sums. Advances in Neural Information Processing Systems (NeurIPS), 2019. [pdf] [supplement]

L. Chizat, E. Oyallon, F. Bach. On Lazy Training in Differentiable Programming. Advances in Neural Information Processing Systems (NeurIPS), 2019. [pdf] [supplement] [poster]

C. Ciliberto, F. Bach, A. Rudi. Localized Structured Prediction. Advances in Neural Information Processing Systems (NeurIPS), 2019. [pdf] [supplement]

J. Altschuler, F. Bach, A. Rudi, J. Niles-Weed. Massively scalable Sinkhorn distances via the Nyström method. Advances in Neural Information Processing Systems (NeurIPS), 2019. [pdf] [supplement]

T. Ryffel, E. Dufour Sans, R. Gay, F. Bach, D. Pointcheval. Partially Encrypted Machine Learning using Functional Encryption. Advances in Neural Information Processing Systems (NeurIPS), 2019. [pdf] [supplement]

K. S. Sesh Kumar, F. Bach, T. Pock. Fast Decomposable Submodular Function Minimization using Constrained Total Variation. Advances in Neural Information Processing Systems (NeurIPS), 2019. [pdf] [supplement]

G. Gidel, F. Bach and S. Lacoste-Julien. Implicit Regularization of Discrete Gradient Dynamics in Linear Neural Networks. Advances in Neural Information Processing Systems (NeurIPS), 2019. [pdf] [supplement]

O. Sebbouh, N. Gazagnadou, S. Jelassi, F. Bach, R. Gower. Towards closing the gap between the theory and practice of SVRG. Advances in Neural Information Processing Systems (NeurIPS), 2019. [pdf] [supplement]

A. Kavis, K. Y. Levy, F. Bach, V. Cevher. UniXGrad: A Universal, Adaptive Algorithm with Optimal Guarantees for Constrained Optimization. Advances in Neural Information Processing Systems (NeurIPS), 2019. [pdf] [supplement]

A. Défossez, N. Usunier, L. Bottou, F. Bach. Music Source Separation in the Waveform Domain. Technical report, arXiv-1911.13254, 2019. [pdf]

A. Défossez, N. Usunier, L. Bottou, F. Bach. Demucs: Deep Extractor for Music Sources with extra unlabeled data remixed. Technical report, arXiv-1909.01174, 2019. [pdf]

F. Bach. Max-plus matching pursuit for deterministic Markov decision processes. Technical report, arXiv-1906.08524, 2019. [pdf]

T. Shpakova, F. Bach, M. E. Davies. Hyper-parameter Learning for Sparse Structured Probabilistic Models. Proceedings of the International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2019. [pdf]

D. Babichev, D. Ostrovskii, F. Bach. Efficient Primal-Dual Algorithms for Large-Scale Multiclass Classification. Technical report, arXiv-1902.03755, 2019. [pdf]

U. Marteau-Ferey, D. Ostrovskii, F. Bach, A. Rudi. Beyond Least-Squares: Fast Rates for Regularized Empirical Risk Minimization through Self-Concordance. Proceedings of the International Conference on Learning Theory (COLT), 2019. [pdf] [poster] [slides] [video]

F. Bach, K. Y. Levy. A Universal Algorithm for Variational Inequalities Adaptive to Smoothness and Noise. Proceedings of the International Conference on Learning Theory (COLT), 2019. [pdf]

A. Taylor, F. Bach. Stochastic first-order methods: non-asymptotic and computer-aided analyses via potential functions. Proceedings of the International Conference on Learning Theory (COLT), 2019. [pdf] [code] [slides] [video]

A. Nowak-Vila, F. Bach, A. Rudi. A General Theory for Structured Prediction with Smooth Convex Surrogates. Technical report, arXiv-1902.01958, 2019. [pdf]

H. V. Vo, F. Bach, M. Cho, K. Han, Y. Le Cun, P. Perez, J. Ponce. Unsupervised Image Matching and Object Discovery as Optimization. Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR), 2019. [pdf]

H. Hendrikx, L. Massoulié, F. Bach. Accelerated Decentralized Optimization with Local Updates for Smooth and Strongly Convex Objectives. Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS), 2019. [pdf]

A. Nowak-Vila, F. Bach, A. Rudi. Sharp Analysis of Learning with Discrete Losses. Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS), 2019. [pdf]

S. Vaswani, F. Bach, M. Schmidt. Fast and Faster Convergence of SGD for Over-Parameterized Models and an Accelerated Perceptron. Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS), 2019. [pdf]

A. Genevay, L. Chizat, F. Bach, M. Cuturi, G. Peyré. Sample Complexity of Sinkhorn divergences. Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS), 2019. [pdf] [supplement]

P. Ablin, A. Gramfort, J.-F. Cardoso, F. Bach. Stochastic algorithms with descent guarantees for ICA. Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS), 2019. [pdf]

A. Podosinnikova, A. Perry, A. Wein, F. Bach, A. d'Aspremont, D. Sontag. Overcomplete Independent Component Analysis via SDP. Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS), 2019. [pdf]

F. Bach. Submodular Functions: from Discrete to Continuous Domains. Mathematical Programming, 175(1), 419-459, 2019. [pdf] [code] [slides]

L. Rencker, F. Bach, W. Wang, M. D. Plumbley. Sparse Recovery and Dictionary Learning From Nonlinear Compressive Measurements. IEEE Transactions in Signal Processing, 67(21):5659-5670, 2019. [pdf]

2018

L. Pillaud-Vivien, A. Rudi, F. Bach. Statistical Optimality of Stochastic Gradient Descent on Hard Learning Problems through Multiple Passes. Advances in Neural Information Processing Systems (NIPS), 2018. [pdf] [supplement][slides]

L. Chizat, F. Bach. On the Global Convergence of Gradient Descent for Over-parameterized Models using Optimal Transport. Advances in Neural Information Processing Systems (NeurIPS), 2018. [pdf] [supplement] [poster]

K. Scaman, F. Bach, S. Bubeck, Y.-T. Lee, L. Massoulié. Optimal Algorithms for Non-Smooth Distributed Optimization in Networks. Advances in Neural Information Processing Systems (NeurIPS), 2018. [pdf] [supplement]

A. Defossez, N. Zeghidour, N. Usunier, L. Bottou, F. Bach. SING: Symbol-to-Instrument Neural Generator. Advances in Neural Information Processing Systems (NeurIPS), 2018. [pdf] [audio samples]

F. Bach. Efficient Algorithms for Non-convex Isotonic Regression through Submodular Optimization. Advances in Neural Information Processing Systems (NeurIPS), 2018. [pdf] [supplement]

J. Tang, M. Golbabaee, F. Bach, M. E. Davies. Rest-Katyusha: Exploiting the Solution's Structure via Scheduled Restart Schemes. Advances in Neural Information Processing Systems (NeurIPS), 2018. [pdf] [supplement]

E. Pauwels, F. Bach, J.-P. Vert. Relating Leverage Scores and Density using Regularized Christoffel Functions. Advances in Neural Information Processing Systems (NeurIPS), 2018. [pdf] [supplement]

D. Scieur, E. Oyallon, A. d'Aspremont, F. Bach. Nonlinear Acceleration of Deep Neural Networks. Technical report, arXiv-1805.09639, 2018. [pdf]

D. Babichev and F. Bach. Constant Step Size Stochastic Gradient Descent for Probabilistic Modeling. Proceedings of the conference on Uncertainty in Artificial Intelligence (UAI), 2018. [pdf]

T. Shpakova, F. Bach and A. Osokin. Marginal Weighted Maximum Log-likelihood for Efficient Learning of Perturb-and-Map models. Proceedings of the conference on Uncertainty in Artificial Intelligence (UAI), 2018. [pdf]

L. Rencker, F. Bach, W. Wang, M. D. Plumbley. Consistent dictionary learning for signal declipping. International Conference on Latent Variable Analysis and Signal Separation, 2018. [pdf]

L. Pillaud-Vivien, A. Rudi, F. Bach. Exponential convergence of testing error for stochastic gradient methods. Proceedings of the International Conference on Learning Theory (COLT), 2018. [pdf]

N. Tripuraneni, N. Flammarion, F. Bach, M. I. Jordan. Averaging Stochastic Gradient Descent on Riemannian Manifolds. Proceedings of the International Conference on Learning Theory (COLT), 2018. [pdf]

D. Babichev and F. Bach. Slice inverse regression with score functions. Electronic Journal of Statistics, 12(1):1507-1543, 2018. [pdf]

R. M. Gower, N. Le Roux, F. Bach. Tracking the gradients using the Hessian: A new look at variance reducing stochastic methods. Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS), 2018. [pdf] [code]

A. Kundu, F. Bach, C. Bhattacharyya. Convex optimization over intersection of simple sets: improved convergence rate guarantees via an exact penalty approach. Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS), 2018. [pdf]

S. Reddi, M. Zaheer, S. Sra, B. Poczos, F. Bach, R. Salakhutdinov, A. Smola. A Generic Approach for Escaping Saddle points. Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS), 2018. [pdf]

M. El Halabi, F. Bach, V. Cevher. Combinatorial Penalties: Which structures are preserved by convex relaxations? Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS), 2018. [pdf]

C. Dupuy and F. Bach. Learning Determinantal Point Processes in Sublinear Time. Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS), 2018. [pdf]

T. Schatz, F. Bach, E. Dupoux. Evaluating automatic speech recognition systems as quantitative models of cross-lingual phonetic category perception. Journal of the Acoustical Society of America, Express Letters, 3(55), 2018. [pdf]

2017

A. Defossez, F. Bach. AdaBatch: Efficient Gradient Aggregation Rules for Sequential and Parallel Stochastic Gradient Methods. Technical Report, Arxiv-1711.01761, 2017. [pdf]

J. Weed, F. Bach. Sharp asymptotic and finite-sample rates of convergence of empirical measures in Wasserstein distance. Technical Report, Arxiv-1707.00087, 2017. To appear in Bernoulli. [pdf]

D. Scieur, A. d'Aspremont, F. Bach. Nonlinear Acceleration of Stochastic Algorithms. Advances in Neural Information Processing Systems (NIPS), 2017. [pdf]

A. Osokin, F. Bach, S. Lacoste-Julien. On Structured Prediction Theory with Calibrated Convex Surrogate Losses. Advances in Neural Information Processing Systems (NIPS), 2017. [pdf]

D. Scieur, V. Roulet, F. Bach, A. d'Aspremont. Integration Methods and Accelerated Optimization Algorithms. Advances in Neural Information Processing Systems (NIPS), 2017. [pdf]

A. Dieuleveut, N. Flammarion, and F. Bach. Harder, Better, Faster, Stronger Convergence Rates for Least-Squares Regression. Journal of Machine Learning Research, 18(101):1?51, 2017. [pdf]

N. Flammarion, P. Balamurugan, F. Bach. Robust Discriminative Clustering with Sparse Regularizers. Journal of Machine Learning Research, 18(80):1-50, 2017. [pdf]

F. Pedregosa, F. Bach, A. Gramfort. On the Consistency of Ordinal Regression Methods. Journal of Machine Learning Research, 18(55):1-35, 2017. [pdf]

F. Bach. On the Equivalence between Kernel Quadrature Rules and Random Feature Expansions. Journal of Machine Learning Research, 18(19):1-38, 2017. [pdf]

F. Bach. Breaking the Curse of Dimensionality with Convex Neural Networks. Journal of Machine Learning Research, 18(19):1-53, 2017. [pdf]

K. Scaman, F. Bach, S. Bubeck, Y.-T. Lee, L. Massoulié. Optimal algorithms for smooth and strongly convex distributed optimization in networks. Proceedings of the International Conference on Machine Learning (ICML), 2017. [pdf]

N. Flammarion, F. Bach. Stochastic Composite Least-Squares Regression with convergence rate O(1/n). Proceedings of the International Conference on Learning Theory (COLT), 2017. [pdf]

R. Rezende, J. Zepeda, J. Ponce, F. Bach, P. Pérez. Kernel square-loss exemplar machines for image retrieval. Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR), 2017. [pdf] [code]

R. Sankaran, F. Bach, C. Bhattacharyya. Identifying groups of strongly correlated variables through Smoothed Ordered Weighted L1-norms. Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS), 2017. [pdf]

C. Dupuy and F. Bach. Online but Accurate Inference for Latent Variable Models with Local Gibbs Sampling. Journal of Machine Learning Research, 18(126):1?45, 2017. [pdf] [code]

K. S. Sesh Kumar, F. Bach. Active-set Methods for Submodular Minimization Problems. Journal of Machine Learning Research, 18(132):1?31, 2017. [pdf]

F. Yanez, F. Bach. Primal-Dual Algorithms for Non-negative Matrix Factorization with the Kullback-Leibler Divergence. Proceedings of the International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2017. [pdf] [code]

T. Schatz, R. Turnbull, F. Bach, E. Dupoux. A Quantitative Measure of the Impact of Coarticulation on Phone Discriminability. Proceedings of INTERSPEECH, 2017. [pdf]

2016

G. Obozinski and F. Bach. A unified perspective on convex structured sparsity: Hierarchical, symmetric, submodular norms and beyond. Technical report, HAL-01412385, 2016. [pdf]

T. Shpakova and F. Bach. Parameter Learning for Log-supermodular Distributions. Advances in Neural Information Processing Systems (NIPS). [pdf]

D. Scieur, A. d'Aspremont, F. Bach. Regularized Nonlinear Acceleration. Advances in Neural Information Processing Systems (NIPS). [pdf]

P. Balamurugan and F. Bach. Stochastic Variance Reduction Methods for Saddle-Point Problems. Advances in Neural Information Processing Systems (NIPS). [pdf] [code]

A. Genevay, M. Cuturi, G. Peyré, F. Bach. Stochastic Optimization for Large-scale Optimal Transport. Advances in Neural Information Processing Systems (NIPS). [pdf]

P. Germain, F. Bach, S. Lacoste-Julien. PAC-Bayesian Theory Meets Bayesian Inference. Advances in Neural Information Processing Systems (NIPS), 2016. [pdf]

M. Schmidt, N. Le Roux, F. Bach. Minimizing Finite Sums with the Stochastic Average Gradient. Mathematical Programming, 162(1):83-112, 2016. [pdf] [code]

A. Dieuleveut, F. Bach. Non-parametric Stochastic Approximation with Large Step sizes. The Annals of Statistics, 44(4):1363-1399, 2016. [pdf]

F. Bach, V. Perchet. Highly-Smooth Zero-th Order Online Optimization. Proceedings of the Conference on Learning Theory (COLT), 2016. [pdf]

A. Podosinnikova, F. Bach, S. Lacoste-Julien. Beyond CCA: Moment Matching for Multi-View Models. Proceedings of the International Conference on Machine Learning (ICML), 2016. [pdf]

R. Lajugie, P. Bojanowski, P. Cuvillier, S. Arlot, F. Bach. A weakly-supervised discriminative model for audio-to-score alignment. Proceedings of the International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2016. [pdf]

2015

A. Podosinnikova, F. Bach, S. Lacoste-Julien. Rethinking LDA: moment matching for discrete ICA. Advances in Neural Information Processing Systems (NIPS), 2015. [pdf]

R. Shivanna, B. Chatterjee, R. Sankaran, C. Bhattacharyya, F. Bach. Spectral Norm Regularization of Orthonormal Representations for Graph Transduction. Advances in Neural Information Processing Systems (NIPS), 2015. [pdf]

P. Bojanowski, R. Lajugie, E. Grave, F. Bach, I. Laptev, J. Ponce and C. Schmid. Weakly-Supervised Alignment of Video With Text. Proceedings of the International Conference on Computer Vision (ICCV), 2015. [pdf]

V. Roulet, F. Fogel, A. d'Aspremont, F. Bach. Supervised Clustering in the Data Cube. Technical Report, ArXiv 1506.04908, 2015. [pdf]

F. Fogel, R. Jenatton, F. Bach, A. d'Aspremont. Convex Relaxations for Permutation Problems. SIAM Journal on Matrix Analysis and Application, 36(4):1465-1488, 2015. [pdf]

N. Flammarion, F. Bach. From Averaging to Acceleration, There is Only a Step-size. Proceedings of the International Conference on Learning Theory (COLT), 2015. [pdf]

R. Lajugie, P. Bojanowski, S. Arlot and F. Bach. Semidefinite and Spectral Relaxations for Multi-Label Classification. Technical report, HAL- 01159321, 2015. [pdf]

K. S. Sesh Kumar, A. Barbero, S. Jegelka, S. Sra, F. Bach. Convex Optimization for Parallel Energy Minimization. Technical report, HAL-01123492, 2015. [pdf]

N. Shervashidze and F. Bach. Learning the Structure for Structured Sparsity. IEEE Transactions on Signal Processing, 63(18):4894-4902. [pdf] [code]

A. Defossez, F. Bach. Averaged Least-Mean-Square: Bias-Variance Trade-offs and Optimal Sampling Distributions. Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS), 2015. [pdf]

S. Lacoste-Julien, F. Lindsten, F. Bach. Sequential Kernel Herding: Frank-Wolfe Optimization for Particle Filtering. Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS), 2015. [pdf]

A. Bietti, F. Bach, A. Cont. An online EM algorithm in hidden (semi-)Markov models for audio segmentation and clustering. Proceedings of the International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2015. [pdf]

F. Bach. Duality between subgradient and conditional gradient methods. SIAM Journal of Optimization, 25(1):115-129, 2015. [pdf]

R. Gribonval, R. Jenatton, F. Bach, M. Kleinsteuber, M. Seibert. Sample Complexity of Dictionary Learning and Other Matrix Factorizations. IEEE Transactions on Information Theory, 61(6):3469-3486, 2015. [pdf]

R. Gribonval, R. Jenatton, F. Bach. Sparse and spurious: dictionary learning with noise and outliers. IEEE Transactions on Information Theory, 61(11): 6298-6319, 2015. [pdf]

2014

J. Mairal, F. Bach, J. Ponce. Sparse Modeling for Image and Vision Processing. Foundations and Trends in Computer Vision, 8(2-3):85-283, 2014. [pdf]

D. Garreau, R. Lajugie, S. Arlot and F. Bach. Metric Learning for Temporal Sequence Alignment. Advances in Neural Information Processing Systems (NIPS), 2014. [pdf]

A. Defazio, F. Bach, S. Lacoste-Julien. SAGA: A Fast Incremental Gradient Method With Support for Non-Strongly Convex Composite Objectives. Advances in Neural Information Processing Systems (NIPS), 2014. [pdf]

P. Bojanowski, R. Lajugie, F. Bach, I. Laptev, J. Ponce, C. Schmid and J. Sivic. Weakly-Supervised Action Labeling in Videos Under Ordering Constraints. Proceedings of the European Conference on Computer Vision (ECCV), 2014. [pdf]

E. Grave, G. Obozinski, F. Bach. A Markovian approach to distributional semantics with application to semantic compositionality. Proceedings of the International Conference on Computational Linguistics (COLING), 2014. [pdf]

R. Lajugie, S. Arlot and F. Bach. Large-Margin Metric Learning for Partitioning Problems. Proceedings of the International Conference on Machine Learning (ICML), 2014. [pdf]

F. Bach. Adaptivity of averaged stochastic gradient descent to local strong convexity for logistic regression. Journal of Machine Learning Research, 15(Feb):595-627, 2014. [pdf]

A. d'Aspremont, F. Bach, L. El Ghaoui. Approximation Bounds for Sparse Principal Component Analysis. Mathematical Programming, 2014. [pdf]

T. Schatz, V. Peddinti, X.-N. Cao, F. Bach, H. Hynek, E. Dupoux. Evaluating Speech Features with the Minimal-Pair ABX task (II): Resistance to Noise. Proceedings of INTERSPEECH, 2014. [pdf]

2013

F. Bach. Learning with Submodular Functions: A Convex Optimization Perspective. Foundations and Trends in Machine Learning, 6(2-3):145-373, 2013. [FOT website] [pdf] [slides]

F. Bach and E. Moulines. Non-strongly-convex smooth stochastic approximation with convergence rate O(1/n). Advances in Neural Information Processing Systems (NIPS). [pdf] [slides] [IPAM slides]

S. Jegelka, F. Bach, S. Sra. Reflection methods for user-friendly submodular optimization. Advances in Neural Information Processing Systems (NIPS). [pdf]

B. Mishra, G. Meyer, F. Bach, R. Sepulchre. Low-rank optimization with trace norm penalty. SIAM Journal on Optimization, 23(4):2124-2149, 2013. [pdf]

F. Fogel, R. Jenatton, F. Bach, A. d'Aspremont. Convex Relaxations for Permutation Problems. Technical report, arXiv:1306.4805, 2013. To appear in Advances in Neural Information Processing Systems (NIPS). [pdf]

K. S. Sesh Kumar and F. Bach. Maximizing submodular functions using probabilistic graphical models. Technical report, HAL 00860575, 2013. [pdf]

A. Nelakanti, C. Archambeau, J. Mairal, F. Bach, G. Bouchard. Structured Penalties for Log-linear Language Models. Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), 2013. [pdf]

P. Bojanowski, F. Bach, I. Laptev, J. Ponce, C. Schmid and J. Sivic. Finding Actors and Actions in Movies. Proceedings of the International Conference on Computer Vision (ICCV), 2013. [pdf]

F. Bach. Convex relaxations of structured matrix factorizations. Technical report, HAL 00861118, 2013. [pdf]

T. Schatz, V. Peddinti, F. Bach, A. Jansen, H. Hynek, E. Dupoux. Evaluating speech features with the Minimal-Pair ABX task: Analysis of the classical MFC/PLP pipeline. Proceedings of INTERSPEECH, 2013. [pdf]

Z. Harchaoui, F. Bach, O. Cappe and E. Moulines. Kernel-Based Methods for Hypothesis Testing: A Unified View. IEEE Signal processing Magazine, 30(4): 87-97, 2013. [pdf]

E. Grave, G. Obozinski, F. Bach. Hidden Markov tree models for semantic class induction. Proceedings of the Conference on Computational Natural Language Learning (CoNLL), 2013. [pdf]

E. Richard, F. Bach, and J.-P. Vert. Intersecting singularities for multi-structured estimation. Proceedings of the International Conference on Machine Learning (ICML), 2013. [pdf]

G. Rigaill, T. D. Hocking, F. Bach, and J.-P. Vert. Learning Sparse Penalties for Change-Point Detection using Max Margin Interval Regression. Proceedings of the International Conference on Machine Learning (ICML), 2013. [pdf]

K. S. Sesh Kumar and F. Bach. Convex relaxations for learning bounded-treewidth decomposable graphs. Proceedings of the International Conference on Machine Learning (ICML), 2013. [pdf]

T. D. Hocking, G. Schleiermacher, I. Janoueix-Lerosey, O. Delattre, F. Bach, J.-P. Vert. Learning smoothing models of copy number profiles using breakpoint annotations. BMC Bioinformatics, 14:1-15, 2013. [pdf]

F. Bach. Sharp analysis of low-rank kernel matrix approximations. Technical report, HAL 00723365. Proceedings of the International Conference on Learning Theory (COLT), 2013. [pdf]

N. Le Roux, F. Bach. Local component analysis. Proceedings of the International Conference on Learning Representations (ICLR), 2013. [pdf]

2012

S. Lacoste-Julien, M. Schmidt, F. Bach. A Simpler Approach to Obtaining an O(1/t) Convergence Rate for the Projected Stochastic Subgradient Method. Technical report arXiv:1212.2002v2, December 2012. [pdf]

R. Jenatton, R. Gribonval and F. Bach. Local stability and robustness of sparse dictionary learning in the presence of noise. Technical report, HAL 00737152, 2012. [pdf]

G. Obozinski and F. Bach. Convex Relaxation for Combinatorial Penalties. Technical report, HAL 00694765, 2012. [pdf]

N. Le Roux, M. Schmidt, F. Bach. A Stochastic Gradient Method with an Exponential Convergence Rate for Strongly-Convex Optimization with Finite Training Sets. Advances in Neural Information Processing Systems (NIPS). Technical report, HAL 00674995, 2012. [pdf] [slides]

H. Kadri, A. Rakotomamonjy, F. Bach, P. Preux. Multiple Operator-valued Kernel Learning. Advances in Neural Information Processing Systems (NIPS). Technical report, HAL 00677012, 2012. [pdf]

R. Jenatton, A. Gramfort, V. Michel, G. Obozinski, E. Eger, F. Bach, B. Thirion. Multi-scale Mining of fMRI data with Hierarchical Structured Sparsity. SIAM Journal on Imaging Sciences, 2012, 5(3):835-856, 2012. [pdf]

M. Solnon, S. Arlot, F. Bach. Multi-task Regression using Minimal Penalties. Journal of Machine Learning Research, 13(Sep):2773-2812, 2012. [pdf]

A. Joulin and F. Bach. A convex relaxation for weakly supervised classifiers. Proceedings of the International Conference on Machine Learning (ICML), 2012. [pdf]

F. Bach, S. Lacoste-Julien, G. Obozinski. On the Equivalence between Herding and Conditional Gradient Algorithms. Proceedings of the International Conference on Machine Learning (ICML), 2012. [pdf]

A. Joulin, F. Bach, J. Ponce. Multi-Class Cosegmentation. Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR), 2012. [pdf]

F. Bach, R. Jenatton, J. Mairal, G. Obozinski. Structured sparsity through convex optimization. Statistical Science, 27(4):450-468, 2012. [pdf] [slides]

F. Bach, R. Jenatton, J. Mairal, G. Obozinski. Optimization with sparsity-inducing penalties. Foundations and Trends in Machine Learning, 4(1):1-106, 2012. [FOT website] [pdf] [slides]

J. Mairal, F. Bach, J. Ponce. Task-Driven Dictionary Learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, 34(4):791-804, 2012. [pdf]   

2011

C. Archambeau, F. Bach. Multiple Gaussian process models. Technical Report Arxiv 110.5238, 2011. [pdf]

F. Bach, E. Moulines. Non-Asymptotic Analysis of Stochastic Approximation Algorithms for Machine Learning. Advances in Neural Information Processing Systems (NIPS), 2011. [pdf] [long-version-pdf-HAL]

M. Schmidt, N. Le Roux, F. Bach. Convergence Rates of Inexact Proximal-Gradient Methods for Convex Optimization. Advances in Neural Information Processing Systems (NIPS), 2011. [pdf] [long-version-pdf-HAL]

E. Grave, G. Obozinski, F. Bach. Trace Lasso: a trace norm regularization for correlated designs. Advances in Neural Information Processing Systems (NIPS), 2011. [pdf] [long-version-pdf-HAL]

F. Bach. Shaping Level Sets with Submodular Functions. Advances in Neural Information Processing Systems (NIPS), 2011. [pdf] [long-version-pdf-HAL]

B. Mishra, G. Meyer, F. Bach, R. Sepulchre. Low-rank optimization with trace norm penalty. Technical report, Arxiv 1112.2318, 2011. [pdf]

R. Jenatton, J.-Y. Audibert and F. Bach. Structured Variable Selection with Sparsity-inducing Norms. Journal of Machine Learning Research, 12, 2777-2824, 2011. [pdf] [code]

J. Mairal, R. Jenatton, G. Obozinski, F. Bach. Convex and Network Flow Optimization for Structured Sparsity. Journal of Machine Learning Research, 12, 2681-2720. [pdf]

R. Jenatton, J. Mairal, G. Obozinski, F. Bach. Proximal Methods for Hierarchical Sparse Coding. Journal of Machine Learning Research, 12, 2297-2334, 2011. [pdf]

F. Couzinie-Devy, J. Mairal, F. Bach and J. Ponce. Dictionary Learning for Deblurring and Digital Zoom. Technical report, HAL : inria- 00627402, 2011. [pdf]

Y-L. Boureau, N. Le Roux, F. Bach, J. Ponce, and Y. LeCun. Ask the locals: multi-way local pooling for image recognition. Proceedings of the International Conference on Computer Vision (ICCV), 2011. [pdf]

S. Arlot, F. Bach. Data-driven Calibration of Linear Estimators with Minimal Penalties. Technical report, HAL 00414774-v2, 2011. [pdf]

A. Lefevre, F. Bach, C. Fevotte. Online algorithms for Nonnegative Matrix Factorization with the Itakura-Saito divergence. Technical report, HAL 00602050, 2011. IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), 2011. [pdf]

T. Hocking, A. Joulin, F. Bach and J.-P. Vert. Clusterpath: an Algorithm for Clustering using Convex Fusion Penalties. Proceedings of the International Conference on Machine Learning (ICML), 2011. [pdf]

L. Benoit, J. Mairal, F. Bach, J. Ponce, Sparse Image Representation with Epitomes. Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR), 2011. [pdf]

A. Lefevre, F. Bach, C. Fevotte, Itakura-Saito nonnegative matrix factorization with group sparsity, Proceedings of the International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2011. [pdf]

F. Bach, R. Jenatton, J. Mairal and G. Obozinski. Convex optimization with sparsity-inducing norms. In S. Sra, S. Nowozin, S. J. Wright., editors, Optimization for Machine Learning, MIT Press, 2011. [pdf]

2010

F. Bach. Convex Analysis and Optimization with Submodular Functions: a Tutorial. Technical report, HAL 00527714, 2010. [pdf]

F. Bach. Structured Sparsity-Inducing Norms through Submodular Functions. Advances in Neural Information Processing Systems (NIPS), 2010. [pdf] [long version, arxiv] [slides]

J. Mairal, R. Jenatton, G. Obozinski, F. Bach. Network Flow Algorithms for Structured Sparsity. Advances in Neural Information Processing Systems (NIPS), 2010. [pdf]

A. Joulin, F. Bach, J.Ponce. Efficient Optimization for Discriminative Latent Class Models. Advances in Neural Information Processing Systems (NIPS), 2010. [pdf]

F. Bach, S. D. Ahipasaoglu, A. d'Aspremont. Convex Relaxations for Subset Selection. Technical report Arxiv 1006-3601. [pdf]

M. Hoffman, D. Blei, F. Bach. Online Learning for Latent Dirichlet Allocation. Advances in Neural Information Processing Systems (NIPS), 2010. [pdf]

F. Bach, S. D. Ahipasaoglu, A. d'Aspremont. Convex Relaxations for Subset Selection. Technical report, ArXiv 1006.3601, 2010. [pdf]

R. Jenatton, J. Mairal, G. Obozinski, F. Bach. Proximal Methods for Sparse Hierarchical Dictionary Learning. Proceedings of the International Conference on Machine Learning (ICML), 2010. [pdf] [slides]

M. Journee, F. Bach, P.-A. Absil and R. Sepulchre. Low-Rank Optimization on the Cone of Positive Semidefinite Matrices. SIAM Journal on Optimization, 20(5):2327-2351, 2010. [pdf] [code]

A. Joulin, F. Bach, J.Ponce. Discriminative Clustering for Image Co-segmentation. Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR), 2010. [pdf] [slides] [code]

Y-L. Boureau, F. Bach, Y. LeCun, J. Ponce. Learning Mid-Level Features For Recognition. Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR), 2010. [pdf]

R. Jenatton, G. Obozinski, F. Bach. Structured Sparse Principal Component Analysis. Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS), 2010. [pdf] [code]

M. Zaslavskiy, F. Bach and J.-P. Vert. Many-to-Many Graph Matching: a Continuous Relaxation Approach. Technical report HAL-00465916, 2010. Proceedings of the European Conference on Machine Learning (ECML). [pdf]

F. Bach. Self-Concordant Analysis for Logistic Regression. Electronic Journal of Statistics, 4, 384-414, 2010. [pdf ]

J. Mairal, F. Bach, J. Ponce, G. Sapiro. Online Learning for Matrix Factorization and Sparse Coding. Journal of Machine Learning Research, 11, 10-60, 2010. [pdf] [code]

A. Cord, F. Bach, D. Jeulin. Texture classification by statistical learning from morphological image processing: application to metallic surfaces. Journal of Microscopy, 239(2), 159-166, 2010. [pdf]

2009

P. Liang, F. Bach, G. Bouchard, M. I. Jordan. Asymptotically Optimal Regularization in Smooth Parametric Models. Advances in Neural Information Processing Systems (NIPS), 2009. [pdf]

S. Arlot, F. Bach. Data-driven Calibration of Linear Estimators with Minimal Penalties. Advances in Neural Information Processing Systems (NIPS), 2009. [techreport HAL 00414774 - pdf]

F. Bach. High-Dimensional Non-Linear Variable Selection through Hierarchical Kernel Learning. Technical report, HAL 00413473, 2009. [pdf] [code] [slides]

J. Mairal, F. Bach, J. Ponce, G. Sapiro and A. Zisserman. Non-Local Sparse Models for Image Restoration. International Conference on Computer Vision (ICCV), 2009. [pdf]

O. Duchenne, I. Laptev, J. Sivic, F. Bach and J. Ponce. Automatic Annotation of Human Actions in Video. International Conference on Computer Vision (ICCV), 2009. [pdf]

J. Mairal, F. Bach, J. Ponce and G. Sapiro. Online dictionary learning for sparse coding. International Conference on Machine Learning (ICML), 2009. [pdf]

O. Duchenne, F. Bach, I. Kweon, and J. Ponce. A tensor-based algorithm for high-order graph matching. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2009. [pdf]

M. Zaslavskiy, F. Bach and J.-P. Vert, Global alignment of protein-protein interaction networks by graph matching methods. Bioinformatics, 25(12):1259-1267, 2009. [pdf]

F. Bach, Model-consistent sparse estimation through the bootstrap, Technical report HAL-00354771, 2009. [pdf]

J. Abernethy, F. Bach, T. Evgeniou, and J.-P. Vert, A New Approach to Collaborative Filtering: Operator Estimation with Spectral Regularization. Journal of Machine Learning Research, 10:803-826, 2009 [pdf]

M. Zaslavskiy, F. Bach and J.-P. Vert, A path following algorithm for the graph matching problem. IEEE Transactions on Pattern Analysis and Machine Intelligence, 31(12), 2227-2242, 2009. [pdf]

K. Fukumizu, F. Bach, and M. I. Jordan. Kernel dimension reduction in regression. Annals of Statistics, 37(4), 1871-1905, 2009. [pdf]

2008

F. Bach, J. Mairal, J. Ponce, Convex Sparse Matrix Factorizations, Technical report HAL-00345747, 2008. [pdf]

F. Bach. Exploring Large Feature Spaces with Hierarchical Multiple Kernel Learning. Advances in Neural Information Processing Systems (NIPS), 2008. [pdf] [HAL tech-report] [matlab code]

J. Mairal, F. Bach, J. Ponce, G. Sapiro and A. Zisserman. Supervised Dictionary Learning. Advances in Neural Information Processing Systems (NIPS), 2008. [pdf]

L. Jacob, F. Bach, J.-P. Vert. Clustered Multi-Task Learning: A Convex Formulation. Advances in Neural Information Processing Systems (NIPS), 2008. [pdf]

Z. Harchaoui, F. Bach, and E. Moulines. Kernel change-point analysis, Advances in Neural Information Processing Systems (NIPS), 2008. [pdf]

C. Archambeau, F. Bach. Sparse probabilistic projections, Advances in Neural Information Processing Systems (NIPS), 2008. [pdf]

A. Rakotomamonjy, F. Bach, S. Canu, and Y. Grandvalet. SimpleMKL. Journal of Machine Learning Research, 9, 2491-2521, 2008. [pdf] [code]

J. Mairal, M. Leordeanu, F. Bach, M. Hebert and J. Ponce. Discriminative Sparse Image Models for Class-Specific Edge Detection and Image Interpretation. Proceedings of the European Conference on Computer Vision (ECCV), 2008. [pdf]

F. Bach. Bolasso: model consistent Lasso estimation through the bootstrap. Proceedings of the Twenty-fifth International Conference on Machine Learning (ICML), 2008. [pdf] [slides]

A. d'Aspremont, F. Bach and L. El Ghaoui. Optimal solutions for sparse principal component analysis. Journal of Machine Learning Research, 9, 1269-1294. [pdf] [source code] [slides]

F. Bach. Consistency of the group Lasso and multiple kernel learning, Journal of Machine Learning Research, 9, 1179-1225, 2008. [pdf] [slides]

F. Bach. Consistency of trace norm minimization, Journal of Machine Learning Research, 9, 1019-1048, 2008. [pdf]

J. Mairal, F. Bach, J. Ponce, G. Sapiro and A. Zisserman. Discriminative Learned Dictionaries for Local Image Analysis, Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR), 2008. [pdf]

F. Bach. Graph kernels between point clouds. Proceedings of the Twenty-fifth International Conference on Machine Learning (ICML), 2008. [pdf]

2007

Z. Harchaoui, F. Bach, and E. Moulines. Testing for Homogeneity with Kernel Fisher Discriminant Analysis, Advances in Neural Information Processing Systems (NIPS) 20, 2007. [pdf] [long version, HAL-00270806, 2008]

F. Bach and Z. Harchaoui. DIFFRAC : a discriminative and flexible framework for clustering, Advances in Neural Information Processing Systems (NIPS) 20, 2007. [pdf] [slides]

A. M. Cord, D. Jeulin and F. Bach. Segmentation of random textures by morphological and linear operators. Proceedings of

the Eigth International Symposium on Mathematical Morphology (ISMM), 2007. [pdf]

A. d'Aspremont, F. Bach and L. El Ghaoui.  Full regularization path for sparse principal component analysis. Proceedings of the Twenty-fourth International Conference on Machine Learning (ICML), 2007. [pdf] [tech-report, arXiv]

A. Rakotomamonjy, F. Bach, S. Canu, and Y. Grandvalet.  More Efficiency in Multiple Kernel Learning, Proceedings of the Twenty-fourth International Conference on Machine Learning (ICML), 2007. [pdf]

Z. Harchaoui and F. Bach. Image classification with segmentation graph kernels, Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR), 2007. [pdf] [presentation]

J. Louradour, K. Daoudi and F. Bach. Feature Space Mahalanobis Sequence Kernels: Application to SVM Speaker Verification.  IEEE Transactions on Audio, Speech and Language Processing, 15 (8), 2465-2475, 2007.

Y. Yamanishi, F. Bach., and J.-P. Vert. Glycan Classification with Tree Kernels, Bioinformatics, 23(10):1211-1216, 2007. [pdf] [web supplements]

K. Fukumizu, F. Bach, A. Gretton. Consistency of Kernel Canonical Correlation Analysis. Journal of Machine Learning Research, 8, 361-383, 2007. [pdf]

2006

J. Abernethy, F. Bach, T. Evgeniou, and J.-P. Vert. Low-rank matrix factorization with attributes. Technical report N24/06/MM, Ecole des Mines de Paris, 2006. [pdf] [ArXiv]

F. Bach, Active learning for misspecified generalized linear models, Advances in Neural Information Processing Systems (NIPS) 19, 2006. [pdf] [tech-report]

F. Bach, M. I. Jordan, Learning spectral clustering, with application to speech separation, Journal of Machine Learning Research, 7, 1963-2001, 2006. [pdf] [speech samples]

F. Bach, D. Heckerman, E. Horvitz, Considering cost asymmetry in learning classifiers, Journal of Machine Learning Research, 7, 1713-1741, 2006. [pdf]

J. Louradour, K. Daoudi, F. Bach, SVM Speaker Verification using an Incomplete Cholesky Decomposition Sequence Kernel. Proc. Odyssey, San Juan, Porto Rico, 2006. [pdf] [slides]

2005

K. Fukumizu, F. Bach, Arthur Gretton. Consistency of Kernel Canonical Correlation Analysis. Advances in Neural Information Processing Systems (NIPS) 18, 2005. [pdf]

F. Bach, M. I. Jordan. Predictive low-rank decomposition for kernel methods. Proceedings of the Twenty-second International Conference on Machine Learning (ICML), 2005. [pdf] [matlab/C code] [slides]

F. Bach, M. I. Jordan. A probabilistic interpretation of canonical correlation analysis. Technical Report 688, Department of Statistics, University of California, Berkeley, 2005 [pdf]

F. Bach, D. Heckerman, E. Horvitz, On the path to an ideal ROC Curve: considering cost asymmetry in learning classifiers, Tenth International Workshop on Artificial Intelligence and Statistics (AISTATS), 2005 [pdf] [pdf, technical report MSR-TR-2004-24] [slides]

F. Bach, M. I. Jordan. Discriminative training of hidden Markov models for multiple pitch tracking, Proceedings of the International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2005 [pdf] [pdf, in French]

2004

F. Bach, M. I. Jordan. Blind one-microphone speech separation: A spectral learning approach. Advances in Neural Information Processing Systems (NIPS) 17, 2004. [pdf] [speech samples] [slides]

F. Bach, R. Thibaux, M. I. Jordan. Computing regularization paths for learning multiple kernels.. Advances in Neural Information Processing Systems (NIPS) 17, 2004. [pdf] [matlab code] [slides]

F. Bach, M. I. Jordan. Learning graphical models for stationary time series, IEEE Transactions on Signal Processing, vol. 52, no. 8, 2189-2199, 2004. [pdf]

F. Bach, G. R. G. Lanckriet, M. I. Jordan. Multiple Kernel Learning, Conic Duality, and the SMO Algorithm. Proceedings of the Twenty-first International Conference on Machine Learning, 2004 [pdf] [tech-report]

K. Fukumizu, F. Bach, M. I. Jordan. Dimensionality reduction for supervised learning with reproducing kernel Hilbert spaces, Journal of Machine Learning Research, 5, 73-99, 2004. [pdf]

2003

F. Bach, M. I. Jordan. Beyond independent components: trees and clusters, Journal of Machine Learning Research, 4, 1205-1233, 2003. [pdf] [matlab code]

F. Bach, M. I. Jordan. Learning spectral clustering, Advances in Neural Information Processing Systems (NIPS) 16, 2004. [pdf] [tech-report]

Kenji Fukumizu, F. Bach, and M. I. Jordan. Kernel dimensionality reduction for supervised learning, Advances in Neural Information Processing Systems (NIPS) 16, 2004. [pdf] [pdf, in Japanese]

F. Bach, M. I. Jordan. Analyse en composantes independantes et reseaux Bayesiens, Dix-neuviÃ¨me colloque GRETSI sur le traitement du signal et des images, 2003. [ps] [pdf] [matlab code]

F. Bach, M. I. Jordan. Finding clusters in independent component analysis, Fourth International Symposium on Independent Component Analysis and Blind Signal Separation, 2003. [pdf] [matlab code]

F. Bach, M. I. Jordan. Kernel independent component analysis, Proceedings of the International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2003. [pdf] [long version (pdf)] [matlab code]

2002

F. Bach, M. I. Jordan. Learning graphical models with Mercer kernels, Advances in Neural Information Processing Systems (NIPS) 15, 2003. [pdf]

F. Bach, M. I. Jordan. Kernel independent component analysis, Journal of Machine Learning Research, 3, 1-48, 2002. [pdf] [matlab code]

F. Bach, M. I. Jordan. Tree-dependent component analysis, Uncertainty in Artificial Intelligence (UAI): Proceedings of the Eighteenth Conference, 2002. [pdf] [matlab code]

2001

F. Bach, M. I. Jordan. Thin junction trees, Advances in Neural Information Processing Systems (NIPS) 14, 2002. [pdf]

Software

Minimizing Finite Sums with the Stochastic Average Gradient
Submodular optimization (matlab)
Discriminative clustering for image co-segmentation (matlab/C)
Structured variable selection with sparsity-inducing norms (matlab)
Structured sparse PCA (matlab)
Sparse modeling software - SPAM (C)
Hierarchical kernel learning - version 3.0 (matlab)
Diffrac - version 1.0 (matlab)
Grouplasso - version 1.0 (matlab)
SimpleMKL - version 1.0 (matlab)
Support Kernel Machine - Multiple kernel learning (matlab)
Predictive low-rank decomposition for kernel methods - version 1.0 (matlab/C)
Computing regularization paths for multiple kernel learning - version 1.0 (matlab)
Tree-dependent component analysis - version 1.0 (matlab)

Tutorials / mini-courses (older ones)

August 2018: Machine Learning Summer School, Madrid - Large-scale machine learning and convex optimization [slides]
September 2017: StatMathAppli 2017, Fréjus - Large-scale machine learning and convex optimization [slides]
May 2017: SIAM Conference on Optimization mini-tutorial on "Stochastic Variance-Reduced Optimization for Machine Learning" [part 1] [part 2]

December 2016: NIPS 2016 Tutorial on "Large-Scale Optimization: Beyond Stochastic Gradient Descent and Convexity" [part 1] [part 2]
July 2016: IFCAM summer school, Indian Institute of Science, Bangalore - Large-scale machine learning and convex optimization [slides]
May 2016: Machine Learning Summer School, Cadiz - Large-scale machine learning and convex optimization [slides]
February 2016: Statistical learning week, CIRM, Luminy - Large-scale machine learning and convex optimization [slides]
January 2016: Winter School on Advances in Mathematics of Signal Processing, Bonn - Large-scale machine learning and convex optimization [slides]
July 2014: IFCAM Summer School, Indian Institute of Science, Bangalore - Large-scale machine learning and convex optimization [slides]
March 2014: YES Workshop, Eurandom, Eindhoven - Large-scale machine learning and convex optimization [slides]
September 2013: Fourth Cargese Workshop on Combinatorial Optimization - Machine learning and convex optimization with submodular functions
September 2012: Machine Learning Summer School, Kyoto - Learning with submodular functions [slides] [notes]
July 2012: Computer Vision and Machine Learning Summer School, Grenoble - Kernel methods and sparse methods for computer vision
July 2012: International Computer Vision Summer School, Sicily - Structured sparsity through convex optimization
July 2011: Computer Vision and Machine Learning Summer School, Paris - Kernel methods and sparse methods for computer vision
September 2010: ECML/PKDD Tutorial on Sparse methods for machine learning (Theory and algorithms)
July 2010: Computer Vision and Machine Learning Summer School, Grenoble - Kernel methods and sparse methods for computer vision
July 2010: Signal processing summer school, Peyresq - Sparse method for machine learning
June 2010: CVPR Tutorial on Sparse Coding and Dictionary Learning for Image Analysis - slides of ML part
December 2009: NIPS Tutorial on Sparse methods for machine learning (Theory and algorithms)
September 2009: ICCV Tutorial on Sparse Coding and Dictionary Learning for Image Analysis
September 2008: Machine Learning Summer School - Ile de Re - Learning with sparsity inducing norms (slides)
October 2008: ECCV Tutorial on Supervised Learning: Introduction - Part I (Theory) - Part II (Algorithms)
January 2008: Workshop RASMA, Franceville, Gabon - Introduction to kernel methods (slides in French)

Courses (older ones)

Fall 2020: Learning theory from first principles - Mastere M2 Mash
Spring 2020: Optimisation et Apprentissage Statistique - Master M2 "Mathematiques de l'aleatoire" - Universite Paris-Sud (Orsay)
Spring 2020: Machine Learning - Masters ICFP, Ecole Normale Superieure