Francis Bach

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

francis dot bach at ens dot fr

francis dot bach at inria dot fr

 

 

 

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

 

 

  Book: Learning Theory from First Principles, to appear in Fall 2024 at MIT Press 

Final draft
Code (python, Matlab)

 

 

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 Superieure/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 have been elected in 2020 at 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 (recent - older ones below)


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]
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]

 

 

Courses (recent - older ones below)


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)
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

 

 

PhD Students and Postdocs


Eugène Berta, co-advised with Michael Jordan
Nabil Boukir, co-advised with Michael Jordan
Sacha Braun, co-advised with Michael Jordan
Bertille Follain
Alexandre François, co-advised with Antonio Orvieto
David Holzmüller
Etienne Gauthier, co-advised with Michael Jordan
Frederik Kunstner
Marc Lambert, co-advised with
Silvère Bonnabel
Ivan Lerner, co-advised with
Anita Burgun and Antoine Neuraz
Simon Martin, co-advised with Giulio Biroli
Fabian Schaipp, co-advised with Umut Simsekli and
Adrien Taylor
Corbinian Schlosser, co-advised with Alessandro Rudi
Lawrence Stewart, co-advised with
Jean-Philippe Vert

 

 

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, Postdoctoral Researcher, Ecole Polytechnique Federale de Lausanne
Alberto Bietti, Postdoctoral Researcher, New York University
Vivien Cabannes, Postdoctoral Researcher, Facebook, New York
Lénaïc Chizat, Assistant Professor, EPFL, Ecole Polytechnique Fédérale de Lausanne

Timothee Cour, Engineer at Google
Hadi Daneshmand, Post-doctoral fellow, Princeton University
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

Nicolas Flammarion, Assistant Professor, Ecole Polytechnique Federale de Lausanne

Fajwel Fogel, Research scientist, Sancare
Rodolphe Jenatton, CTO, Bioptimus
Armand Joulin, Research scientist, Facebook AI Research, Paris
Hans Kersting, Research Scientist, Yahoo Research
Ziad Kobeissi, Researcher at 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

Augustin Lefèvre, Data scientist, YKems
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
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
Adrien Taylor, Research scientist, Inria Paris
Blake Woodworth, Assistant Professor, George Washington University
Mikhail Zaslavskiy, Byopt

 

 

Publications

2024

 

A. H. Ribeiro, T. B. Schön, D. Zachariah, F. Bach. Efficient Optimization Algorithms for Linear Adversarial Training. Technical report, arXiv: 2410.12677, 2024. [pdf]

S. G. Gruber, F. Bach. Optimizing Estimators of Squared Calibration Errors in Classification. Technical report, arXiv:
2410.07014, 2024. [pdf]

N. Doumèche, F. Bach, G. Biau, C. Boyer. Physics-informed kernel learning. Technical report, arXiv:
2409.13786, 2024. [pdf]

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. Technical report, arXiv:
2408.16543, 2024. [pdf]

B. Follain, F. Bach. Enhanced Feature Learning via Regularisation: Integrating Neural Networks and Kernel Methods. Technical report, arXiv:2407.17280, 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. Technical report, arXiv:
2404.14806, 2024. [pdf]

C. Moucer, A. Taylor, F. Bach. Geometry-dependent matching pursuit: a transition phase for convergence on linear regression and LASSO. Technical report, arXiv:
2403.03072, 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. Rudi, U. Marteau-Ferey, F. Bach. Finding Global Minima via Kernel Approximations. 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]

 

2023

 
B. Follain, F. Bach. Nonparametric Linear Feature Learning in Regression Through Regularisation. Technical report, arXiv:2307.12754, 2023. [pdf]

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]

D. Holzmüller, F. Bach. Convergence rates for non-log-concave sampling and log-partition estimation. Technical report, arXiv:2303.0323, 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 AdagradTransactions 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 SquaresProceedings of the Conference on Learning Theory (COLT), 2022. [pdf]

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

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

Y. Sun, F. Bach. Screening for a Reweighted Penalized Conditional Gradient MethodOpen 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 objectivesOpen Journal of Mathematical Optimization, 3(1), 2022. [
pdf]

U. Marteau-Ferey, A. Rudi, F. Bach. Sampling from Arbitrary Functions via PSD ModelsProceedings 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 learningAdvances in Neural Information Processing Systems (NeurIPS), 2021. [
pdf]

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

F. Bach. On the Effectiveness of Richardson Extrapolation in Data ScienceSIAM 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 EstimationProceedings of the Conference on Learning Theory (COLT), 2021. [
pdf]

V. Cabannes, F. Bach, A. Rudi. Fast rates in structured predictionProceedings 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 DualityProceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS), 2021. [
pdf]

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

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

R. M. Gower, P. Richtárik, F. Bach. Stochastic Quasi-Gradient Methods: Variance Reduction via Jacobian SketchingMathematical 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 ReductionAdvances 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 OptimizersAdvances 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 ApproachProceedings 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 NetworksProceedings of the International Conference on Machine Learning (ICML), 2020. [pdf]

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

M. Ballu, Q. Berthet, F. Bach. Stochastic Optimization for Regularized Wasserstein EstimatorsProceedings 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 LossProceedings 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 DistributionsProceedings 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 IterationsSIAM Journal on Mathematics of Data Science 2(1):24-47, 2020. [
pdf]

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

R. M. Gower, M. Schmidt, F. Bach. P. Richtárik. Variance-Reduced Methods for Machine LearningProceedings 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 NetworksJournal 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 LossesAdvances 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 ProgrammingAdvances in Neural Information Processing Systems (NeurIPS), 2019. [
pdf] [supplement] [poster]

 

C. Ciliberto, F. Bach, A. Rudi. Localized Structured PredictionAdvances 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 methodAdvances 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 EncryptionAdvances 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 VariationAdvances 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 NetworksAdvances 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 SVRGAdvances 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 OptimizationAdvances in Neural Information Processing Systems (NeurIPS), 2019. [
pdf] [supplement]

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 ModelsProceedings 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 NoiseProceedings 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 functionsProceedings 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 OptimizationProceedings 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 LossesProceedings 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 PerceptronProceedings 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 divergencesProceedings 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 ICAProceedings 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 SDPProceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS), 2019. [
pdf]

F. Bach. Submodular Functions: from Discrete to Continuous DomainsMathematical 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 MeasurementsIEEE 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 PassesAdvances 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 TransportAdvances 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 NetworksAdvances in Neural Information Processing Systems (NeurIPS), 2018. [
pdf] [supplement]

 

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

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


E. Pauwels, F. Bach, J.-P. Vert. Relating Leverage Scores and Density using Regularized Christoffel FunctionsAdvances 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 ModelingProceedings 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 modelsProceedings 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 declippingInternational 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 methodsProceedings 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 ManifoldsProceedings of the International Conference on Learning Theory (COLT), 2018. [
pdf]

D. Babichev and F. Bach. Slice inverse regression with score functionsElectronic 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 methodsProceedings 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 approachProceedings 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 pointsProceedings 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 TimeProceedings 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 perceptionJournal 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 AlgorithmsAdvances in Neural Information Processing Systems (NIPS), 2017. [pdf]

 

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

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

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

 

N. Flammarion, P. Balamurugan, F. Bach. Robust Discriminative Clustering with Sparse RegularizersJournal 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 ExpansionsJournal 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 retrievalProceedings 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 SamplingJournal of Machine Learning Research, 18(126):1?45, 2017. [
pdf] [code]

 

K. S. Sesh Kumar, F. Bach. Active-set Methods for Submodular Minimization ProblemsJournal 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 DivergenceProceedings 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 DiscriminabilityProceedings 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 DistributionsAdvances in Neural Information Processing Systems (NIPS). [pdf]

 

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

 

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


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

 

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

 

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

 

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


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


A. Podosinnikova, F. Bach, S. Lacoste-Julien. Beyond CCA: Moment Matching for Multi-View ModelsProceedings 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 alignmentProceedings 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 ICAAdvances 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 TransductionAdvances 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 TextProceedings 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 ProblemsSIAM 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-sizeProceedings 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 SparsityIEEE 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 DistributionsProceedings 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 FilteringProceedings 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 clusteringProceedings of the International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2015. [pdf]

F. Bach. Duality between subgradient and conditional gradient methodsSIAM 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 FactorizationsIEEE 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 ProcessingFoundations 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 AlignmentAdvances 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 ObjectivesAdvances 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 ConstraintsProceedings 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 ProblemsProceedings 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 AnalysisMathematical 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 NoiseProceedings 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 penaltySIAM 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 ModelsProceedings 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 pipelineProceedings of INTERSPEECH, 2013. [
pdf]

Z. Harchaoui, F. Bach, O. Cappe and E. Moulines. Kernel-Based Methods for Hypothesis Testing: A Unified ViewIEEE 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 estimationProceedings 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 RegressionProceedings 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 annotationsBMC 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 analysisProceedings 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 SetsAdvances 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 SparsitySIAM Journal on Imaging Sciences, 2012, 5(3):835-856, 2012. [
pdf]

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

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

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

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

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

J. Mairal, F. Bach, J. Ponce. Task-Driven Dictionary LearningIEEE 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 LearningAdvances 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 OptimizationAdvances 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 designsAdvances in Neural Information Processing Systems (NIPS), 2011. [
pdf] [long-version-pdf-HAL]

F. Bach. Shaping Level Sets with Submodular FunctionsAdvances 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 SparsityJournal of Machine Learning Research, 12, 2681-2720. [
pdf]

R. Jenatton, J. Mairal, G. Obozinski, F. Bach. Proximal Methods for Hierarchical Sparse CodingJournal 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 PenaltiesProceedings of the International Conference on Machine Learning (ICML), 2011. [
pdf]

L. Benoit, J. Mairal, F. Bach, J. Ponce, Sparse Image Representation with EpitomesProceedings 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 sparsityProceedings 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 FunctionsAdvances 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 SparsityAdvances in Neural Information Processing Systems (NIPS), 2010. [
pdf]

A. Joulin, F. Bach, J.PonceEfficient Optimization for Discriminative Latent Class ModelsAdvances 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 AllocationAdvances 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 LearningProceedings 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 MatricesSIAM Journal on Optimization, 20(5):2327-2351, 2010. [
pdf] [code]

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

R. Jenatton, G. Obozinski, F. Bach. Structured Sparse Principal Component AnalysisProceedings 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 RegressionElectronic 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 surfacesJournal of Microscopy, 239(2), 159-166, 2010. [
pdf]


2009


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

S. Arlot, F. Bach. Data-driven Calibration of Linear Estimators with Minimal PenaltiesAdvances 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 RestorationInternational Conference on Computer Vision (ICCV), 2009. [
pdf]

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

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

O. Duchenne, F. Bach, I. Kweon, and J. Ponce. A tensor-based algorithm for high-order graph matchingIEEE 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 RegularizationJournal 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 regressionAnnals of Statistics, 37(4), 1871-1905, 2009. [
pdf


2008

 

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

 

F. Bach. Exploring Large Feature Spaces with Hierarchical Multiple Kernel LearningAdvances 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 LearningAdvances in Neural Information Processing Systems (NIPS), 2008. [
pdf]

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

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

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


A. Rakotomamonjy, F. Bach, S. Canu, and Y. Grandvalet.  SimpleMKLJournal 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 InterpretationProceedings 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 analysisJournal 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 minimizationJournal 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 cloudsProceedings 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 AnalysisAdvances 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 clusteringAdvances 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 operatorsProceedings 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 analysisProceedings 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 kernelsProceedings 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 KernelsBioinformatics, 23(10):1211-1216, 2007.  [
pdf] [web supplements]

K. Fukumizu, F. Bach, A. Gretton. Consistency of Kernel Canonical Correlation AnalysisJournal 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 modelsAdvances in Neural Information Processing Systems (NIPS) 19, 2006. [
pdf] [tech-report]

 

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

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

 

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


2005

K. Fukumizu, F. Bach, Arthur Gretton. Consistency of Kernel Canonical Correlation AnalysisAdvances 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 classifiersTenth 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 seriesIEEE 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 AlgorithmProceedings 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 clustersJournal of Machine Learning Research, 4, 1205-1233, 2003. [pdf] [matlab code]

 

F. Bach, M. I. Jordan. Learning spectral clusteringAdvances 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 BayesiensDix-neuvième 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 kernelsAdvances in Neural Information Processing Systems (NIPS) 15, 2003. [pdf]

 

F. Bach, M. I. Jordan. Kernel independent component analysisJournal 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)

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 2014YES 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 2018
: Statistical machine learning - Master M1 - Ecole Normale Superieure (Paris)
Fall 2018
Statistical machine learning - Master M1 - Ecole Normale Superieure (Paris)
Spring 2018
Optimisation et Apprentissage Statistique - Master M2 "Mathematiques de l'aleatoire" - Universite Paris-Sud (Orsay)ematiques, Vision, Apprentissage" - Ecole Normale Superieure de Cachan
Fall 2017
Statistical machine learning - Master M1 - Ecole Normale Superieure (Paris)
Spring 2017Optimisation et Apprentissage Statistique - Master M2 "Mathematiques de l'aleatoire" - Universite Paris-Sud (Orsay)ematiques, Vision, Apprentissage" - Ecole Normale Superieure de Cachan
Spring 2016Optimisation et Apprentissage Statistique - Master M2 "Mathematiques de l'aleatoire" - Universite Paris-Sud (Orsay)ematiques, Vision, Apprentissage" - Ecole Normale Superieure de Cachan
Fall 2014
Statistical machine learning - Master M1 - Ecole Normale Superieure (Paris)
Fall 2014An introduction to graphical models - Master M2 "Mathematiques, Vision, Apprentissage" - Ecole Normale Superieure de Cachan 
Spring 2014Statistical machine learning - Master M2 "Probabilites et Statistiques" - Universite Paris-Sud (Orsay)ematiques, Vision, Apprentissage" - Ecole Normale Superieure de Cachan 
Spring 2013Statistical machine learning - Master M2 "Probabilites et Statistiques" - Universite Paris-Sud (Orsay)
Spring 2013Statistical machine learning - Filiere Math/Info - L3 - Ecole Normale Superieure (Paris)
Spring 2012Statistical machine learning - Filiere Math/Info - L3 - Ecole Normale Superieure (Paris)
Spring 2012Statistical machine learning - Master M2 "Probabilites et Statistiques" - Universite Paris-Sud (Orsay)
Fall 2011An introduction to graphical models - Master M2 "Mathematiques, Vision, Apprentissage" - Ecole Normale Superieure de Cachan
Spring 2011Statistical machine learning - Master M2 "Probabilites et Statistiques" - Universite Paris-Sud (Orsay)
Fall 2010
An introduction to graphical models - Master M2 "Mathematiques, Vision,Apprentissage" - Ecole Normale Superieure de Cachan 
Spring 2010
Statistical machine learning - Master M2 "Probabilites et Statistiques" - Universite Paris-Sud (Orsay)
Fall 2009
An introduction to graphical models - Master M2 "Mathematiques, Vision,Apprentissage" - Ecole Normale Superieure de Cachan 
Fall 2008
An introduction to graphical models - Master M2 "Mathematiques, Vision, Apprentissage" - Ecole Normale Superieure de Cachan 
May 2008Probabilistic modelling and graphical models: Enseignement Specialise - Ecole des Mines de Paris
Fall 2007
An introduction to graphical models - Master M2 "Mathematiques, Vision, Apprentissage" - Ecole Normale Superieure de Cachan
May 2007
Probabilistic modelling and graphical models: Enseignement Specialise - Ecole des Mines de Paris
Fall 2006
An introduction to graphical models - Master M2 "Mathematiques, Vision, Apprentissage" - Ecole Normale Superieure de Cachan
Fall 2005
An introduction to graphical models - Master M2 "Mathematiques, Vision, Apprentissage" - Ecole Normale Superieure de Cachan