Francis Bach

INRIA - Willow project
D
épartement d'Informatique, Ecole Normale Supérieure
45, rue d'Ulm

75230 Paris Cedex
France



Comment rejoindre mon bureau?

 



Je suis chercheur à l' INRIA, dans le projet Willow, localisé au sein de l'Ecole Normale Supérieure. J'ai récemment obtenu ma thèse du département d'informatique de l'Université de Californie à Berkeley, sous la direction du Professeur Michael Jordan, et j'ai passé deux ans au centre de Morphologie Mathematique de l'Ecole des Mines de Paris. Mon domaine de recherches est l'apprentissage automatique, et en particulier les modèles graphiques probabilistes, les méthodes à noyaux et le traitement du signal et des images. [CV (pdf)]

 

Cours:

1er semestre 2005-2006: Introduction aux modèles graphiques - Master M2 "Mathématiques, Vision, Apprentissage" - Ecole Normale Supérieure de Cachan
1er semestre 2006-2007: Introduction aux modèles graphiques - Master M2 "Mathématiques, Vision, Apprentissage" - Ecole Normale Supérieure de Cachan
1er semestre 2007-2008: Introduction aux modèles graphiques - Master M2 "Mathématiques, Vision, Apprentissage" - Ecole Normale Supérieure de Cachan
Mai 2007: Modélisation probabiliste et modèles graphiques - Enseignement Spécialisé - Ecole des Mines de Paris

September 2008Machine Learning Summer School - Ile de Re - Learning with sparsity inducing norms



Groupe de lecture Apprentissage - ParisTech



Publications:

2008


F. Bach. Exploring Large Feature Spaces with Hierarchical Multiple Kernel LearningAdvances in Neural Information Processing Systems (NIPS) 20, to appear, 2008. [HAL tech-report

K. Fukumizu, F. R. Bach, and M. I. Jordan. Kernel dimension reduction in regression. Annals of Statistics, to appear, 2008. [pdf


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]

  M. Journée, F. Bach, P.-A. Absil and R. Sepulchre. Low-rank optimization for semidefinite convex problems. Tecnical report ArXiv 0807.4423v1, 2008. [pdf] [code]


  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. [pdf] [slides]

 F. Bach. Consistency of trace norm minimizationJournal of Machine Learning Research,  9, 1019-1048. [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]


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]


J. Abernethy, F. Bach, T. Evgeniou, and J.-P. Vert, A New Approach to Collaborative Filtering: Operator Estimation with Spectral Regularization. Technical Report HAL-00250231, 2008. [pdf]


M. Zaslavskiy, F. Bach and J.-P. Vert, A path following algorithm for the graph matching problem. Technical Report HAL-00232851, 2008. [pdf]


A. Rakotomamonjy, F. Bach, S. Canu, and Y. Grandvalet.  SimpleMKL, Technical report HAL-00218338, 2008, to appear in Journal of Machine Learning Research. [pdf] [code]



2007



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. R. 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. R. 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, In Press, 2007.  [pdf] [web supplements]

Kenji Fukumizu, Francis R. Bach, Arthur Gretton. Consistency of Kernel Canonical Correlation AnalysisJournal of Machine Learning Research, 8, 361-383, 2006. [pdf]

 
2006

Jacob Abernethy, Francis Bach, Theodoros Evgeniou, and Jean-Philippe Vert. Low-rank matrix factorization with attributes. Technical report N24/06/MM, Ecole des Mines de Paris, 2006. [pdf] [ArXiv]

Francis R. Bach, Active learning for misspecified generalized linear models, Advances in Neural Information Processing Systems (NIPS) 19, 2006. [pdf] [rapport technique

Francis R. Bach, Michael I. Jordan, Learning spectral clustering, with application to speech separation,  Journal of Machine Learning Research, 7, 1963-2001, 2006. [pdf] [examples de signaux]


Francis R. Bach, David Heckerman, Eric Horvitz, Considering cost asymmetry in learning classifiersJournal of Machine Learning Research, 7, 1713-1741, 2006. [pdf]


Jérôme Louradour, Khalid Daoudi, Francis Bach, SVM Speaker Verification using an Incomplete Cholesky Decomposition Sequence Kernel. Proc. Odyssey, San Juan, Porto Rico, 2006. [pdf] [transparents]


2005

Kenji Fukumizu, Francis R. Bach, Arthur Gretton. Consistency of Kernel Canonical Correlation AnalysisAdvances in Neural Information Processing Systems (NIPS) 18, 2005. [pdf] [rapport technique]


Francis R. Bach, Michael I. Jordan. Predictive low-rank decomposition for kernel methods. Proceedings of the Twenty-second International Conference on Machine Learning (ICML), 2005. [pdf] [code Matlab/C] [présentation]
 

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


Francis R. Bach, David Heckerman, Eric 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] [présentation]

Francis R. Bach, Michael 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, en français]

 

2004
 

Francis R. Bach, Michael I. Jordan. Blind one-microphone speech separation: A spectral learning approach. In press, Advances in Neural Information Processing Systems (NIPS) 17, 2004. [pdf] [exemples] [présentation]
 

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

 

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

Francis R. Bach, Gert R. G. Lanckriet, Michael 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]


Kenji Fukumizu, Francis R. Bach, Michael 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
 

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

 

Francis R. Bach, Michael I. Jordan. Learning spectral clustering, Advances in Neural Information Processing Systems (NIPS) 16, 2004. [pdf] [ps.gz] [tech-report]

 

Kenji Fukumizu, Francis R. Bach, and Michael I. Jordan. Kernel dimensionality reduction for supervised learning, Advances in Neural Information Processing Systems (NIPS) 16, 2004. [ps.gz] [pdf] [pdf, en japonais]
 

Francis R. Bach, Michael I. Jordan. Analyse en composantes indépendantes et réseaux Bayésiens, Dix-neuvième colloque GRETSI sur le traitement du signal et des images, 2003. [ps] [pdf] [matlab code]

 

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


Francis R. Bach, Michael I. Jordan. Kernel independent component analysis, Proceedings of the International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2003 [ps] [pdf] [version longue (pdf)] [code matlab]

2002

 

Francis R. Bach, Michael I. Jordan. Learning graphical models with Mercer kernels, Advances in Neural Information Processing Systems (NIPS) 15, 2003. [ps.gz] [pdf]

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

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

 

 

2001

 

Francis R. Bach, Michael I. Jordan. Thin junction trees, Advances in Neural Information Processing Systems (NIPS) 14, 2002. [ps.gz] [pdf]

 

2000

 

Francis Bach et Dimitri Spoliansky, La télévision et le ministre, Gazette de la Société et des Techniques, Juillet 2000. [pdf] [version longue]

 


Logiciels:

Kernel independent component analysis - version 1.2 (matlab)
Tree-dependent component analysis - version 1.0 (matlab)

Computing regularization paths for multiple kernel learning - version 1.0 (matlab)

Predictive low-rank decomposition for kernel methods - version 1.0 (matlab/C)

Support Kernel Machine - Multiple kernel learning (matlab)

 SimpleMKL - version 1.0 (matlab)

Grouplasso - version 1.0 (matlab)