Francis Bach

Francis Bach

INRIA - SIERRA project-team
Laboratoire d'Informatique de l'Ecole Normale Superieure 
23, avenue d'Italie

CS 81321
75214 Paris Cedex 13

francis dot bach at ens dot fr

francis dot bach at inria dot fr


Directions to my office (French)

Directions to my office (English)

 


With David Blei, we are chairing the program committee of the International Conference on Machine Learning (ICML 2015), that will take place in Lille, France, July 6-11, 2015.

Tutorials - Courses - Students - Alumni - Publications - Software

ERC
SIERRA: sparse structured methods for machine learning
ERC-funded project


I am a researcher at INRIA, leading since 2011 the SIERRA project-team, which is part of the Computer Science Laboratory at Ecole Normale Superieure. 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 from 2007 to 2010. I am interested in statistical machine learning, and especially in graphical models, sparse methods, kernel-based learning, convex optimization vision and signal processing. [CV (English)] [CV (French)]
 

Tutorials / mini-courses


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 2008Machine 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


Fall 2014: Statistical machine learning - Master M1 - Ecole Normale Superieure (Paris)
Fall 2014
:
An introduction to graphical models - Master M2 "Mathematiques, Vision, Apprentissage" - Ecole Normale Superieure de Cachan 
Spring 2014
:
Statistical machine learning - Master M2 "Probabilites et Statistiques" - Universite Paris-Sud (Orsay)

Fall 2013: An introduction to graphical models - Master M2 "Mathematiques, Vision, Apprentissage" - Ecole Normale Superieure de Cachan 
Spring 2013
: Statistical machine learning - Master M2 "Probabilites et Statistiques" - Universite Paris-Sud (Orsay)

Spring 2013: Statistical machine learning - Filiere Math/Info - L3 - Ecole Normale Superieure (Paris)
Fall 2012: An introduction to graphical models - Master M2 "Mathematiques, Vision, Apprentissage" - Ecole Normale Superieure de Cachan 
Spring 2012: Statistical machine learning - Filiere Math/Info - L3 - Ecole Normale Superieure (Paris)

Spring 2012: Statistical machine learning - Master M2 "Probabilites et Statistiques" - Universite Paris-Sud (Orsay)

Fall 2011: An introduction to graphical models - Master M2 "Mathematiques, Vision, Apprentissage" - Ecole Normale Superieure de Cachan 

Spring 2011: Statistical 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 2008: Probabilistic 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




SMILE: Statistical Machine Learning in Paris : seminar / reading group


Students and Postdocs


Louise Benoit, co-advised with Jean Ponce
Amit Bermanis
Florent Couzinie-Devy, co-advised with Jean Ponce
Aymeric Dieuleveut
Christophe Dupuy, co-advised with Christophe Diot
Nicolas Flammarion, co-advised with Alexandre d'Aspremont
Fajwel Fogel, co-advised with Alexandre d'Aspremont
Sesh Kumar
Remi Lajugie, co-advised with Sylvain Arlot
Fabian Pedregosa, co-advised with Alexandre Gramfort
Anastasia Podissinikova, co-advised with Simon Lacoste-Julien
Thomas Schatz, co-advised with Emmanuel Dupoux



Alumni

Timothee Cour, Engineer at Google
Edouard Grave, Postdoctoral Researcher, U.C. Berkeley
Toby Hocking, Postdoctoral Researcher, Tokyo Institute of Technology

Rodolphe Jenatton, Machine Learning Scientist, Amazon, Germany
Armand Joulin, Research scientist, Facebook AI lab
Simon Lacoste-Julien, Research faculty at INRIA (Sierra)
Augustin Lefevre, Postdoctoral Researcher, Universite Catholique de Louvain
Nicolas Le Roux, Criteo
Ronny Luss, Researcher, IBM Research
Julien Mairal, Researcher at INRIA, Grenoble
Bamdev Mishra, Postdoctoral Researcher, University of Cambridge
Anil Nelakanti, visiting faculty, Indian Institute of Technology, Varanasi
Guillaume Obozinski, Researcher at Certis, Ecole des Ponts et Chaussees
Mark Schmidt, Assistant professor, University of British Columbia
Nino Shervashidze, Postdoc at Institut Curie

Matthieu Solnon, Professeur de Mathématiques, CPGE, Lycée Lavoisier
Mikhail Zaslavskiy, Researcher at Cellectis



Publications

2014

A. Dieuleveut, F. Bach. Non-parametric Stochastic Approximation with Large Step sizes. Technical report, HAL 01053831, 2014. [pdf]

A. Defazio, F. Bach, S. Lacoste-Julien. SAGA: A Fast Incremental Gradient Method With Support for Non-Strongly Convex Composite Objectives. Technical report, HAL 01016843, 2014. [pdf]

R. Gribonval, R. Jenatton, F. Bach. Sparse and spurious: dictionary learning with noise and outliers. Technical report, HAL 01025503, 2014. [pdf]

E. Grave, G. Obozinski, F. Bach. A Markovian approach to distributional semantics with application to semantic compositionalityProceedings 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]

N. Shervashidze and F. Bach. Learning to Learn for Structured Sparsity. Technical report, HAL 00986380, 2014. [pdf] [code]


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]


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). Technical report, HAL 00831977, 2013. To appear in Advances in Neural Information Processing Systems (NIPS). [pdf] [slides] [IPAM slides]

S. Jegelka, F. Bach, S. Sra. Reflection methods for user-friendly submodular optimization. Technical report, HAL 00905258, 2013. To appear in 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]

M. Schmidt, N. Le Roux, F. Bach. Minimizing Finite Sums with the Stochastic Average Gradient. Technical report, HAL 00860051, 2013. [pdf] [code]

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]

F. Bach. Duality between subgradient and conditional gradient methods. Technical report, HAL 00757696-v3, 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 inductionProceedings 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]

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


K. S. Sesh Kumar and F. Bach. Convex Relaxations for Learning Bounded Treewidth Decomposable Graphs. Technical report, HAL 00763921, 2012. Proceedings of the International Conference on Machine Learning (ICML). [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]

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. Technical report, HAL  00663790, 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 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 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 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.Ponce. Efficient 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 Matrices. SIAM 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 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 ApproachTechnical 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 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 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 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 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 bootstrapProceedings 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 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 VerificationIEEE 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 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 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 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 Kernel. Proc. 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 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. [ps.gz] [pdf]
 

 

2003
 

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

 

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

F. Bach, M. I. Jordan. Analyse en composantes independantes et reseaux Bayesiens, Dix-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. [ps] [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 [ps] [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. [ps.gz] [pdf]

 

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

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

 

 

2001

 

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






Workshop on Big data: theoretical and practical challenges'': May, 14-15, 2013 @ IHP, Paris, France
Slides available

Fete Parisienne in Computation, Inference and Optimization: A Young Researchers' Forum­: March 20, 2013 @ IHES, France
Slides available

MGA: Projet ANR Modeles graphiques et applications