2013

  • Thomas Ricatte, Gemma Garriga, Rémi Gilleron, Marc Tommasi. Learning from Multiple Graphs using a Sigmoid Kernel. Proceedings of ICMLA 2013. (accepted paper).
  • Pascal Germain, Amaury Habrard, Francois Laviolette, Emilie Morvant.A PAC-Bayesian Approach for Domain Adaptation with Specialization to Linear Classifiers. Proceedings of ICML, JMLR W&CP 28 (3): 738–746, 2013
  • Mattias Gybels, François Denis , Amaury Habrard. Utilisation de matrices de Hankel non bornées pour l'apprentissage spectral de langages stochastiques. Actes de la conférence d'Apprentissage, 2013.
  • Amaury Habrard, Jean-Philippe Peyrache, Marc Sebban: Boosting for Unsupervised Domain Adaptation. ECML/PKDD (2) 2013: 433-448
  • Amaury Habrard, Jean-Philippe Peyrache, Marc Sebban: Iterative Self-labeling Domain Adaptation for Linear Structured Image Classification, International Journal on Artificial Intelligence Tools (2013)
  • Basura Fernando, Amaury Habrard, Marc Sebban, Tinne Tuytelaars: Unsupervised Visual Domain Adaptation Using Subspace Alignment, 14th International Conference on Computer Vision - ICCV 2013
  • Aurélien Bellet, Amaury Habrard, Marc Sebban: A Survey on Metric Learning for Feature Vectors and Structured Data. arXiv:1306.6709, (2013)
  • H. Kadri, M. Ghavamzadeh, Ph. Preux, A Generalized Kernel Approach to Structured Output Learning, Proc. ICML, JMLR W&CP 28(1):471-479, Atlanta, Jun. 2013

2012

T0+36

  • A. Bellet, A. Habrard, M. Sebban. Good edit similarity learning by loss minimization. Machine Learning, 2012, 89(1-2), 5-35.
  • A. Bellet, A. Habrard, M. Sebban. Similarity Learning for Provably Accurate Sparse Linear Classification. International Conference on Machine Learning (ICML), 2012.
  • Jean Baptiste Faddoul, Boris Chidlovskii, Rémi Gilleron, Fabien Torre. Learning Multiple Tasks with Boosted Decision Trees. ECML/PKDD - European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases - 2012.
  • Antonino Freno, Mikaela Keller, Gemma Garriga, Marc Tommasi: "Spectral Estimation of Conditional Random Graph Models for Large-Scale Network data". UAI 2012 - 28th Conference on Uncertainty in Artificial Intelligence.
  • Antonino Freno, Mikaela Keller, Marc Tommasi: Fiedler Random Fields: A Large-Scale Spectral Approach to Statistical Network Modeling. NIPS 2012.
  • H. Kadri, A. Rakotomamonjy, F. Bach, Ph. Preux, Multiple Operator-valued Kernel Learning, in Proc. NIPS, 2012
  • G. Arnold-Dulac, L. Denoyer, Ph. Preux, P. Gallinari, Sequential Approaches for Learning Datum-Wise Sparse Representations, in Machine Learning, 89(1-2), 87-122, 2012.
  • G. Dulac-Arnold, L. Denoyer, Ph. Preux, P. Gallinari, Fast Reinforcement Learning with Large Action Sets using Error-Correcting Output Codes for MDP Factorization, in the proceedings of the ECML-PKDD 2012, Springer, LNAI, Bristol, Sep. 2012
  • O. Nicol and J. Mary and Ph. Preux, ICML Exploration & Exploitation challenge: Keep it simple!, in Journal of Machine Learning Research W&CP, 26, 62:85, 2012.
  • Victor Gabillon, Mohammad Ghavamzadeh, Alessandro Lazaric. "Best Arm Identification: A Unified Approach to Fixed Budget and Fixed Confidence," Proceedings of the Twenty-Sixth Annual Conference on Advances in Neural Information Processing Systems (NIPS-2012), 2012.
  • Daniil Ryabko, Jeremie Mary. "Reducing statistical time-series problems to binary classification," Proceedings of the Twenty-Sixth Annual Conference on Advances in Neural Information Processing Systems (NIPS-2012), 2012.
  • Ronald Ortner, Daniil Ryabko. "Online Regret Bounds for Undiscounted Continuous Reinforcement Learning," Proceedings of the Twenty-Sixth Annual Conference on Advances in Neural Information Processing Systems (NIPS-2012), 2012.
  • Azadeh Khaleghi, Daniil Ryabko. "Locating Changes in Highly-Dependent Data with Unknown Number of Change Points," Proceedings of the Twenty-Sixth Annual Conference on Advances in Neural Information Processing Systems (NIPS-2012), 2012.
  • Ronald Ortner, Daniil Ryabko, Peter Auer and Remi Munos, "Regret Bounds for Restless Markov Bandits," In Proceedings of ALT 2012.

T0+30

  • Amaury Habrard, Jean-Philippe Peyrache, Marc Sebban. "Un Cadre Formel de Boosting pour l'Adaptation de Domaine". Conférence d'Apprentissage (CAP 2012).
  • Aurélien Bellet, Amaury Habrard, Marc Sebban. "Apprentissage de bonnes similarités et classification linéaire parcimonieuse", Conférence d'Apprentissage (CAP 2012).
  • Antonino Freno: "Semiparametric Pseudo-Likelihood Estimation in Markov Random Fields". In: Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics (AISTATS). JMLR W&CP, 2012.
  • Azadeh Khaleghi, Daniil Ryabko, Jeremie Mary, Philippe Preux. "Online Clustering of Processes," In: Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics (AISTATS). JMLR W&CP 22: 601-609, 2012.
  • G. Dulac-Arnold, L. Denoyer, Ph. Preux, P. Gallinari, Apprentissage par renforcement rapide pour des grands ensembles d'actions en utilisant des codes correcteurs d'erreur, JFPDA et CAP, Nancy, Mai 2012
  • Bruno Scherrer, Mohammad Ghavamzadeh, Victor Gabillon, Matthieu Geist. "Approximate Modified Policy Iteration," Proceedings of the Twenty-Ninth International Conference on Machine Learning (ICML-2012), pp. 1207-1214, Edinburgh, Scotland, 2012.
  • Matthieu Geist, Bruno Scherrer, Alessandro Lazaric, and Mohammad Ghavamzadeh. "A Dantzig Selector Approach to Temporal Difference Learning," Proceedings of the Twenty-Ninth International Conference on Machine Learning (ICML-2012), pp. 1399-1406, Edinburgh, Scotland, 2012.
  • Mohammad Ghavamzadeh and Alessandro Lazaric. "Conservative and Greedy Approaches to Classification-based Policy Iteration," Proceedings of the Twenty-Sixth Conference on Artificial Intelligence (AAAI-2012), pp. 914-920, Toronto, ON, Canada, 2012.
  • D. Ryabko Testing composite hypotheses about discrete ergodic processes. Test vol. 21(2), pp. 317-329, 2012.

2011

  • Victor Gabillon, Mohammad Ghavamzadeh, Alessandro Lazaric, and Sebastien Bubeck. "Multi-Bandit Best Arm Identification". Proceedings of the Twenty-Fifth Annual Conference on Advances in Neural Information Processing Systems (NIPS-2011), pp. 2222-2230, 2011.
  • O. Maillard, R. Munos, D. Ryabko. "Selecting the State-Representation in Reinforcement Learning," In Proceedings of NIPS, Granada, Spain, pp. 2627-2635, 2011.
  • Antonino Freno, Gemma Garriga, Mikaela Keller: Learning to Recommend Links using Graph Structure and Node Content. Neural Information Processing Systems Workshop on Choice Models and Preference Learning. 2011.
  • Aurélien Bellet, Amaury Habrard, Marc Sebban. "An Experimental Study on Learning with Good Edit Similarity Functions". Proceedings of the 23rd IEEE International Conference on Tools with Artificial Intelligence. Pages 126-133. 2011.
  • Marc Bernard , Jean-Philippe Peyrache, Marc Sebban, Franck Thollard. "Using the H-divergence to Prune Probabilistic Automata". Proceedings of the 23rd IEEE International Conference on Tools with Artificial Intelligence - Pages 725-731. 2011.
  • Amaury Habrard, Jean-Philippe Peyrache, Marc Sebban. "Domain Adaptation with Good Edit Similarities: a Sparse Way to deal with Scaling and Rotation Problems in Image Classification". Proceedings of the 23rd IEEE International Conference on Tools with Artificial Intelligence. Pages 181-188. 2011 (best paper award - sélectionné pour un numéro spécial à IJAIT).

T0+24

  • Raphaël Bailly, François Denis: "Absolute convergence of rational series is semi-decidable". Inf. Comput. 209(3): 280-295 (2011)
  • Raphaël Bailly: "QWA: Spectral Algorithm". Proceedings of ICMLA. Journal of Machine Learning Research - Proceedings Track 20: 147-163 (2011).
  • Alessandro Lazaric, Mohammad Ghavamzadeh, and Remi Munos. "Finite-Sample Analysis of Least-Squares Policy Iteration," Accepted for publication at the Journal of Machine Learning Research (JMLR), 2011.
  • Raphaël Bailly, Amaury Habrard and François Denis. A Spectral Approach for Probabilistic Grammatical Inference on Trees. Proceedings of the 21st International Conference on Algorithmic Theory (ALT) 2011, pp. 74-88, LNCS 6331, Springer.
  • Aurélien Bellet, Amaury Habrard, Marc Sebban. Learning Good Edit Similarities with Generalization Guarantees. ECML/PKDD 2011
  • Gabriel Dulac-Arnold, Philippe Preux, Ludovic Denoyer, Patrick Gallinari. Datum-Wise Classification: A Sequential Approach to Sparsity ECML/PKDD 2011 (Task 2.2)
  • H. Kadri, A. Rabaoui, Ph. Preux, E. Duflos, A. Rakotomamonjy, Functional Regularized Least Squares Classification with Operator-Valued Kernels, in Proc. 28th International Conference on Machine Learning (ICML), Seattle, June 2011
  • H. Kadri, Ph. Preux, E. Duflos, S. Canu, Multiple functional regression with both discrete and continuous covariates, in Proc. 2nd International Workshop on Functional and Operatorial Statistics (IWFOS), Santander, June 2011

T0+18

  • H. Kadri, Ph. Preux, E. Duflos, Régression ridge à noyau pour des variables explicatives et d'intérêts fonctionnelles, in Proc. 43e Journées de statistiques (JDS), Mai 2011
  • H. Kadri, E. Duflos, Ph. Preux, Learning vocal tract variables with multi-task kernels, in Proc. 36th International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 821-826, Prague, Czech Republic, May 2011
  • Gabriel Dulac-Arnold, Ludovic Denoyer, Patrick Gallinari: Text Classification: A Sequential Reading Approach. ECIR 2011: 411-423
  • Mohammad Ghavamzadeh, Alessandro Lazaric, Rémi Munos, & Matthew Hoffman. Finite-Sample Analysis of Lasso-TD, Proceedings of the Twenty-Eighth International Conference on Machine Learn- ing (ICML-2011), Bellevue, WA, June 2011. (Task 2.3)
  • Pierre Machart, Thomas Peel, Sandrine Anthoine, Liva Ralaivola, Hervé Glotin. Stochastic Low-Rank Kernel Learning for Regression. Proceedings of the Twenty-Eighth International Conference on Machine Learning (ICML-2011).
  • Raphaël Bailly. Automates Quadratiques Pondérés. Conférence d'Apprentissage (CAp) 2011
  • Aurélien Bellet, Amaury Habrard, Marc Sebban. Apprentissage parcimonieux à partir de fonctions de similarité d'édition (ϵ,γ,τ)-good. Conférence d'Apprentissage (CAp) 2011.

2010

  • Mohammad Ghavamzadeh, Alessandro Lazaric, Odalric Maillard, & Rémi Munos. LSTD with Random Projections, Proceedings of the Twenty-Fourth Annual Conference on Advances in Neural Information Processing Systems (NIPS- 2010), pp. 721-729, 2010.(Task 2.3)

T0+12

  • Aurélien Bellet, Marc Bernard, Thierry Murgue, Marc Sebban: Learning state machine-based string edit kernels. Pattern Recognition 43,(6), 2330-2339 (2010)
  • Odalric Maillard, Rémi Munos, Alessandro Lazaric, & Mohammad Ghavamzadeh. Finite-Sample Analysis of Bellman Residual Minimization. Proceedings of the Second Asian Conference on Machine Learning (ACML-2010), pp. 299-314, Tokyo, Japan, November, 2010.(Task 2.3)
  • Édouard Gilbert, Rémi Gilleron and Marc Tommasi. Series, Weighted Automata, Probabilistic Automata and Probability Distributions for Unranked Trees. Rapport de Recherche INRIA.
  • D. Ryabko. Clustering processes. In Proceedings of 27th International Conference on Machine Learning (ICML), Haifa, Israel, pp. 919-926, 2010
  • D. Ryabko. On Finding Predictors for Arbitrary Families of Processes. Journal of Machine Learning Research, vol. 11(Feb): 581-602, 2010.
  • D. Ryabko, Discrimination between B-processes is impossible. Journal of Theoretical Probability, 23(2):565-575, 2010.