Bibliography

Publications of the year

Doctoral Dissertations and Habilitation Theses

• 1E. Grave.
  A Markovian approach to distributional semantics, Université Pierre et Marie Curie - Paris VI, January 2014.
  http://hal.inria.fr/tel-00940575
• 2M. Solnon.
  Apprentissage statistique multi-tâches, Université Pierre et Marie Curie - Paris VI, November 2013.
  http://hal.inria.fr/tel-00911498

Articles in International Peer-Reviewed Journals

• 3Z. Harchaoui, F. Bach, O. Cappé, E. Moulines.
  Kernel-Based Methods for Hypothesis Testing: A Unified View, in: IEEE Signal Processing Magazine, June 2013, vol. 30, n^o 4, pp. 87-97. [ DOI : 10.1109/MSP.2013.2253631 ]
  http://hal.inria.fr/hal-00841978
• 4B. Mishra, G. Meyer, F. Bach, R. Sepulchre.
  Low-rank optimization with trace norm penalty, in: SIAM Journal on Optimization, 2013, vol. 23, n^o 4, pp. 2124-2149. [ DOI : 10.1137/110859646 ]
  http://hal.inria.fr/hal-00924110
• 5A. d'Aspremont, N. E. Karoui.
  Weak Recovery Conditions from Graph Partitioning Bounds and Order Statistics, in: Mathematics of Operations Research, July 2013, vol. 38, n^o 2, Final version.
  http://pubsonline.informs.org/doi/abs/10.1287/moor.1120.0581, http://hal.inria.fr/hal-00907541

International Conferences with Proceedings

• 6A. Ahmed, N. Shervashidze, S. Narayanamurthy, V. Josifovski, A. J. Smola.
  Distributed Large-scale Natural Graph Factorization, in: IW3C2 - International World Wide Web Conference, Rio de Janeiro, Brazil, May 2013, 37 p.
  http://hal.inria.fr/hal-00918478
• 7F. Bach.
  Sharp analysis of low-rank kernel matrix approximations, in: International Conference on Learning Theory (COLT), United States, 2013.
  http://hal.inria.fr/hal-00723365
• 8F. Bach, E. Moulines.
  Non-strongly-convex smooth stochastic approximation with convergence rate O(1/n), in: Neural Information Processing Systems (NIPS), United States, 2013.
  http://hal.inria.fr/hal-00831977
• 9P. Bojanowski, F. Bach, I. Laptev, J. Ponce, C. Schmid, J. Sivic.
  Finding Actors and Actions in Movies, in: ICCV 2013 - IEEE International Conference on Computer Vision, Sydney, Australia, IEEE, 2013.
  http://hal.inria.fr/hal-00904991
• 10M. Cuturi, A. d'Aspremont.
  Mean Reversion with a Variance Threshold, in: International Conference on Machine Learning, United States, October 2013, pp. 271-279.
  http://hal.inria.fr/hal-00939566
• 11M. Eickenberg, F. Pedregosa, S. Mehdi, A. Gramfort, B. Thirion.
  Second order scattering descriptors predict fMRI activity due to visual textures, in: PRNI 2013 - 3nd International Workshop on Pattern Recognition in NeuroImaging, Philadelphia, United States, Conference Publishing Services, June 2013.
  http://hal.inria.fr/hal-00834928
• 12F. Fogel, R. Jenatton, F. Bach, A. d'Aspremont.
  Convex Relaxations for Permutation Problems, in: Neural Information Processing Systems (NIPS) 2013, United States, August 2013.
  http://nips.cc/Conferences/2013/Program/speaker-info.php?ID=12863, http://hal.inria.fr/hal-00907528
• 13E. Grave, G. Obozinski, F. Bach.
  Hidden Markov tree models for semantic class induction, in: CoNLL - Seventeenth Conference on Computational Natural Language Learning, Sofia, Bulgaria, 2013.
  http://hal.inria.fr/hal-00833288
• 14P. Gronat, G. Obozinski, J. Sivic, T. Pajdla.
  Learning and calibrating per-location classifiers for visual place recognition, in: CVPR 2013 - 26th IEEE Conference on Computer Vision and Pattern Recognition, Portland, United States, June 2013.
  http://hal.inria.fr/hal-00934332
• 15S. Jegelka, F. Bach, S. Sra.
  Reflection methods for user-friendly submodular optimization, in: NIPS 2013 - Neural Information Processing Systems, Lake Tahoe, Nevada, United States, 2013.
  http://hal.inria.fr/hal-00905258
• 16S. Lacoste-Julien, M. Jaggi, M. Schmidt, P. Pletscher.
  Block-Coordinate Frank-Wolfe Optimization for Structural SVMs, in: ICML 2013 International Conference on Machine Learning, Atlanta, United States, 2013, pp. 53-61.
  http://hal.inria.fr/hal-00720158
• 17S. Lacoste-Julien, K. Palla, A. Davies, G. Kasneci, T. Graepel, Z. Ghahramani.
  SiGMa: Simple Greedy Matching for Aligning Large Knowledge Bases, in: KDD 2013 - The 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Chicago, United States, August 2013, pp. 572-580. [ DOI : 10.1145/2487575.2487592 ]
  http://hal.inria.fr/hal-00918671
• 18N. Le Roux, F. Bach.
  Local Component Analysis, in: ICLR - International Conference on Learning Representations 2013, Scottsdale, United States, 2013.
  http://hal.inria.fr/inria-00617965
• 19A. Nelakanti, C. Archambeau, J. Mairal, F. Bach, G. Bouchard.
  Structured Penalties for Log-linear Language Models, in: EMNLP - Empirical Methods in Natural Language Processing - 2013, Seattle, United States, Association for Computational Linguistics, October 2013, pp. 233-243.
  http://hal.inria.fr/hal-00904820
• 20F. Pedregosa, M. Eickenberg, B. Thirion, A. Gramfort.
  HRF estimation improves sensitivity of fMRI encoding and decoding models, in: 3nd International Workshop on Pattern Recognition in NeuroImaging, Philadelphia, United States, May 2013.
  http://hal.inria.fr/hal-00821946
• 21E. Richard, F. Bach, J.-P. Vert.
  Intersecting singularities for multi-structured estimation, in: ICML 2013 - 30th International Conference on Machine Learning, Atlanta, United States, 2013.
  http://hal.inria.fr/hal-00918253
• 22G. Rigaill, T. D. Hocking, F. Bach, J.-P. Vert.
  Learning Sparse Penalties for Change-Point Detection using Max Margin Interval Regression, in: ICML 2013 - 30 th International Conference on Machine Learning, Atlanta, United States, Supported by the International Machine Learning Society (IMLS), May 2013.
  http://hal.inria.fr/hal-00824075
• 23T. Schatz, V. Peddinti, F. Bach, A. Jansen, H. Hermansky, E. Dupoux.
  Evaluating speech features with the Minimal-Pair ABX task: Analysis of the classical MFC/PLP pipeline, in: INTERSPEECH 2013 : 14th Annual Conference of the International Speech Communication Association, Lyon, France, 2013, pp. 1-5.
  http://hal.inria.fr/hal-00918599
• 24K. S. Sesh Kumar, F. Bach.
  Convex Relaxations for Learning Bounded Treewidth Decomposable Graphs, in: International Conference on Machine Learning, Atlanta, United States, 2013, Extended version of the ICML-2013 paper..
  http://hal.inria.fr/hal-00763921

Conferences without Proceedings

• 25E. Grave, G. Obozinski, F. Bach.
  Domain adaptation for sequence labeling using hidden Markov models, in: New Directions in Transfer and Multi-Task: Learning Across Domains and Tasks (NIPS Workshop), Lake Tahoe, United States, 2013.
  http://hal.inria.fr/hal-00918371

Scientific Books (or Scientific Book chapters)

• 26F. Bach.
  Learning with Submodular Functions: A Convex Optimization Perspective, Foundations and Trends in Machine Learning, Now Publishers, 2013, 228 p. [ DOI : 10.1561/2200000039 ]
  http://hal.inria.fr/hal-00645271

Other Publications

• 27F. Bach.
  Adaptivity of averaged stochastic gradient descent to local strong convexity for logistic regression, October 2013.
  http://hal.inria.fr/hal-00804431
• 28F. Bach.
  Convex relaxations of structured matrix factorizations, September 2013.
  http://hal.inria.fr/hal-00861118
• 29F. Fogel, I. Waldspurger, A. d'Aspremont.
  Phase retrieval for imaging problems, 2013.
  http://hal.inria.fr/hal-00907529
• 30R. Gribonval, R. Jenatton, F. Bach, M. Kleinsteuber, M. Seibert.
  Sample Complexity of Dictionary Learning and other Matrix Factorizations, December 2013, submitted.
  http://hal.inria.fr/hal-00918142
• 31R. Lajugie, S. Arlot, F. Bach.
  Large-Margin Metric Learning for Partitioning Problems, March 2013.
  http://hal.inria.fr/hal-00796921
• 32M. Schmidt, N. Le Roux, F. Bach.
  Minimizing Finite Sums with the Stochastic Average Gradient, September 2013.
  http://hal.inria.fr/hal-00860051
• 33M. Schmidt, N. Le Roux.
  Fast Convergence of Stochastic Gradient Descent under a Strong Growth Condition, August 2013.
  http://hal.inria.fr/hal-00855113
• 34K. S. Sesh Kumar, F. Bach.
  Maximizing submodular functions using probabilistic graphical models, September 2013.
  http://hal.inria.fr/hal-00860575
• 35M. Solnon.
  Comparison bewteen multi-task and single-task oracle risks in kernel ridge regression, 2013, Submitted to the Electronic Journal of Statistics.
  http://hal.inria.fr/hal-00846715
• 36I. Waldspurger, A. d'Aspremont, S. Mallat.
  Phase Recovery, MaxCut and Complex Semidefinite Programming, 2013, Submitted revision.
  http://hal.inria.fr/hal-00907535
• 37A. d'Aspremont, M. Jaggi.
  An Optimal Affine Invariant Smooth Minimization Algorithm, 2013.
  http://hal.inria.fr/hal-00907547

References in notes

• 38F. Bach.
  Learning with Submodular Functions: A Convex Optimization Perspective, in: ArXiv e-prints, 2011.
• 39F. Bach, M. Jordan.
  Thin junction trees, in: Adv. NIPS, 2002.
• 40F. Bach, M. Jordan.
  Learning spectral clustering, in: Adv. NIPS, 2003.
• 41A. Bar-Hillel, T. Hertz, N. Shental, D. Weinshall.
  Learning a mahalanobis metric from equivalence constraints, in: Journal of Machine Learning Research, 2006, vol. 6, n^o 1, 937 p.
• 42C. Bishop, et al..
  Pattern recognition and machine learning, springer New York, 2006.
• 43D. Blatt, A. O. Hero, H. Gauchman.
  A convergent incremental gradient method with a constant step size, in: SIOPT, 2007, vol. 18, n^o 1, pp. 29–51.
• 44Y. Boykov, O. Veksler, R. Zabih.
  Fast approximate energy minimization via graph cuts, in: IEEE Trans. PAMI, 2001, vol. 23, n^o 11, pp. 1222–1239.
• 45L. Burget, P. Matejka, P. Schwarz, O. Glembek, J. Cernocky.
  Analysis of Feature Extraction and Channel Compensation in a GMM Speaker Recognition System, in: IEEE Transactions on Audio, Speech and Language Processing, September 2007, vol. 15, n^o 7, pp. 1979-1986.
• 46M. A. Carlin, S. Thomas, A. Jansen, H. Hermansky.
  Rapid evaluation of speech representations for spoken term discovery, in: Proceedings of Interspeech, 2011.
• 47Y.-W. Chang, M. Collins.
  Exact Decoding of Phrase-based Translation Models through Lagrangian Relaxation, in: Proceedings of the Conference on Empirical Methods for Natural Language Processing, 2011, pp. 26–37.
• 48A. Chechetka, C. Guestrin.
  Efficient Principled Learning of Thin Junction Trees, in: Adv. NIPS, 2007.
• 49J. Chen, A. K. Gupta.
  Parametric Statistical Change Point Analysis, Birkhäuser, 2011.
• 50S. Chen, R. Rosenfeld.
  A survey of smoothing techniques for ME models, in: IEEE Transactions on Speech and Audio Processing, 2000, vol. 8, n^o 1, pp. 37–50.
• 51Y. Cheng.
  Mean shift, mode seeking, and clustering, in: IEEE Trans. PAMI, 1995, vol. 17, n^o 8, pp. 790–799.
• 52C. I. Chow, C. N. Liu.
  Approximating discrete probability distributions with dependence trees, in: IEEE Trans. Inf. Theory, 1968, vol. 14.
• 53F. De la Torre, T. Kanade.
  Discriminative cluster analysis, in: Proc. ICML, 2006.
• 54F. Desobry, M. Davy, C. Doncarli.
  An online kernel change detection algorithm, in: IEEE Trans. Sig. Proc., 2005, vol. 53, n^o 8, pp. 2961–2974.
• 55B. Efron, C. N. Morris.
  Stein's paradox in statistics, in: Scientific American, 1977, vol. 236, pp. 119–127.
• 56T. Evgeniou, C. A. Micchelli, M. Pontil.
  Learning Multiple Tasks with Kernel Methods, in: Journal of Machine Learning Research, 2005, vol. 6, pp. 615–637.
• 57P. Fousek, P. Svojanovsky, F. Grezl, H. Hermansky.
  New Nonsense Syllables Database – Analyses and Preliminary ASR Experiments, in: Proceedings of the International Conference on Spoken Language Processing (ICSLP), 2004, pp. 2004-29.
• 58S. Fujishige.
  Submodular Functions and Optimization, Annals of Discrete Mathematics, Elsevier, 2005.
• 59V. Gogate, W. Webb, P. Domingos.
  Learning Efficient Markov Networks, in: Adv. NIPS, 2010.
• 60J. Goodman.
  A bit of progress in language modelling, in: Computer Speech and Language, October 2001, pp. 403–434.
• 61J. C. Gower, G. J. S. Ross.
  Minimum spanning trees and single linkage cluster analysis, in: Applied statistics, 1969, pp. 54–64.
• 62T. D. Hocking, G. Schleiermacher, I. Janoueix-Lerosey, O. Delattre, F. Bach, J.-P. Vert.
  Learning smoothing models of copy number profiles using breakpoint annotations, in: HAL, archives ouvertes, 2012.
• 63L. Jacob, F. Bach, J.-P. Vert.
  Clustered Multi-Task Learning: A Convex Formulation, in: Computing Research Repository, 2008, pp. -1–1.
• 64W. James, C. Stein.
  Estimation with quadratic loss, in: Proceedings of the fourth Berkeley symposium on mathematical statistics and probability, 1961, vol. 1, n^o 1961, pp. 361–379.
• 65R. Jenatton, J. Mairal, G. Obozinski, F. Bach.
  Proximal Methods for Hierarchical Sparse Coding, in: Journal of Machine Learning Research, 2011, pp. 2297-2334.
• 66R. Kneser, H. Ney.
  Improved backing-off for m-gram language modeling, in: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, 1995, vol. 1.
• 67D. Koller, N. Friedman.
  Probabilistic graphical models: principles and techniques, MIT press, 2009.
• 68V. Kolmogorov, T. Schoenemann.
  Generalized sequential tree-reweighted message passing, in: ArXiv e-prints, May 2012.
• 69A. Krause, C. Guestrin.
  Submodularity and its Applications in Optimized Information Gathering, in: ACM Transactions on Intelligent Systems and Technology, 2011, vol. 2, n^o 4.
• 70H. Lin, J. Bilmes.
  A Class of Submodular Functions for Document Summarization, in: Proc. NAACL/HLT, 2011.
• 71D. Luenberger, Y. Ye.
  Linear and nonlinear programming, Springer Verlag, 2008.
• 72N. A. Macmillan, C. D. Creelman.
  Detection theory: A user's guide, Lawrence Erlbaum, 2004.
• 73F. Malvestuto.
  Approximating discrete probability distributions with decomposable models, in: IEEE Trans. Systems, Man, Cybernetics, 1991, vol. 21, n^o 5.
• 74A. F. T. Martins, N. A. Smith, A. M. Q. Pedro, M. A. T. Figueiredo.
  Structured sparsity in structured prediction, in: Proceedings of the Conference on Empirical Methods for Natural Language Processing, 2011, pp. 1500–1511.
• 75M. Narasimhan, J. Bilmes.
  PAC-learning bounded tree-width graphical models, in: Proc. UAI, 2004.
• 76G. Nemhauser, L. Wolsey, M. Fisher.
  An analysis of approximations for maximizing submodular set functions–I, in: Mathematical Programming, 1978, vol. 14, n^o 1, pp. 265–294.
• 77A. Nemirovski, A. Juditsky, G. Lan, A. Shapiro.
  Robust stochastic approximation approach to stochastic programming, in: SIOPT, 2009, vol. 19, n^o 4, pp. 1574–1609.
• 78A. Nemirovski.
  Efficient methods in convex programming, in: Lecture notes, 1994.
• 79Y. Nesterov.
  Introductory lectures on convex optimization: A basic course, Springer, 2004.
• 80A. Y. Ng, M. Jordan, Y. Weiss.
  On spectral clustering: Analysis and an algorithm, in: Adv. NIPS, 2002.
• 81B. Roark, M. Saraclar, M. Collins, M. Johnson.
  Discriminative language modeling with conditional random fields and the perceptron algorithm, in: Proceedings of the Association for Computation Linguistics, 2004.
• 82L. Saul, M. Jordan.
  Exploiting Tractable Substructures in Intractable Networks, in: Adv. NIPS, 1995.
• 83H. D. Sherali, W. P. Adams.
  A Hierarchy of Relaxations Between the Continuous and Convex Hull Representations for Zero-One Programming Problems, in: SIAM J. Discrete Math., 1990.
• 84J. Shi, J. Malik.
  Normalized Cuts and Image Segmentation, in: IEEE Trans. PAMI, 1997, vol. 22, pp. 888–905.
• 85GSVS. Sivaram, H. Hermansky.
  Sparse Multilayer Perceptron for Phoneme Recognition, in: IEEE Transactions on Audio, Speech, and Language Processing, 2012, vol. 20, n^o 1, pp. 23-29.
• 86M. Solnon, S. Arlot, F. Bach.
  Multi-task Regression using Minimal Penalties, in: Journal of Machine Learning Research, September 2012, vol. 13, pp. 2773-2812.
• 87M. Solodov.
  Incremental gradient algorithms with stepsizes bounded away from zero, in: Computational Optimization and Applications, 1998, vol. 11, n^o 1, pp. 23–35.
• 88C. Stein.
  Inadmissibility of the usual estimator for the mean of a multivariate normal distribution, in: Proceedings of the Third Berkeley symposium on mathematical statistics and probability, 1956, vol. 1, n^o 399, pp. 197–206.
• 89T. Szántai, E. Kovács.
  Discovering a junction tree behind a Markov network by a greedy algorithm, in: ArXiv e-prints, April 2011.
• 90P. Tseng.
  An incremental gradient(-projection) method with momentum term and adaptive stepsize rule, in: SIOPT, 1998, vol. 8, n^o 2, pp. 506-531.
• 91I. Tsochantaridis, T. Hofmann, T. Joachims, Y. Altun.
  Support Vector Machine Learning for Interdependent and Structured Output Spaces, in: Proc. ICML, 2004.
• 92S. Vargas, P. Castells, D. Vallet.
  Explicit relevance models in intent-oriented information retrieval diversification, in: Proceedings of the 35th ACM SIGIR International Conference on Research and development in information retrieval, Portland, Oregon, USA, SIGIR'12, ACM, 2012, pp. 75-84.
  http://doi.acm.org/10.1145/2348283.2348297
• 93M. Wainwright, M. Jordan.
  Graphical models, exponential families, and variational inference, in: Found. and Trends in Mach. Learn., 2008, vol. 1, n^o 1-2.
• 94F. Wood, C. Archambeau, J. Gasthaus, J. Lancelot, Y.-W. Teh.
  A Stochastic Memoizer for Sequence Data, in: Proceedings of the 26th International Conference on Machine Learning, 2009.
• 95E. P. Xing, A. Y. Ng, M. Jordan, S. Russell.
  Distance metric learning with applications to clustering with side-information, in: Adv. NIPS, 2002.
• 96P. Zhao, G. Rocha, B. Yu.
  The composite absolute penalties family for grouped and hierarchical variable selection, in: The Annals of Statistics, 2009, vol. 37(6A), pp. 3468-3497.