photo Matthieu Lerasle

Matthieu Lerasle

logo cnrs logo UPSA


  1. Mean estimation for Randomized Quasi Monte Carlo method, with E. Gobet and D. Métivier (2022), hal-03631879v10.
  2. Optimal Change-Point Detection and Localization, with M. Fromont, P. Reynaud-Bouret and N. Verzelen (2020), arXiv:2010.11470.
  3. Pair Matching: When bandits meet stochastic block model, with C. Giraud, Y. Issartel and L. Lehéricy, (2019), arXiv:1905.07342.
  4. A Bayesian nonparametric approach for generalized Bradley-Terry models in random environment, with S. Le Corff and E. Vernet, (2018), arXiv:1808.08104.

Publiés et Acceptés

  1. Benign overfitting in the large deviation regime, with G. Chinot, accepted for publication at Bernoulli, (2022), arXiv:2003.05838.
  2. Median of means principle as a divide-and-conquer procedure for robustness, sub-sampling and hyper-parameters tuning, with J. Kwon and G. Lecué, Electron. J. Stat., 15, 1, (2021), 1202-1227, arXiv:1812.02435.
  3. Cross-validation improved by aggregation: Agghoo, with G. Maillard and S. Arlot, accepted for publication in J. Mach. Learn. Res., (2020), arXiv:1709.03702.
  4. Robust high dimensional learning for Lipschitz and convex losses, with G. Chinot and G. Lecué, J. Mach. Learn. Res., 21, 233, (2020), 1-47, arXiv:1905.04281.
  5. Learning the distribution of latent variables in paired comparison models, with R. Diel and S. Le Corff, Bernoulli, 26, 4, (2020), 2670-2698. arXiv:1707.01365.
  6. A quantitative Mc Diarmid's inequality for geometrically ergodic Markov chains, with A. Havet, E. Moulines and E. Vernet, Electron. Commun. Probab., 25, (2020), arXiv:1907.02809.
  7. Robust classification via MOM minimization, with G. Lecué and T. Mathieu, Mach. Learn. 109, 8, (2020), 1635-1665, arXiv:1808.03106.
  8. Statistical learning with Lipschitz and convex loss functions, with G. Chinot and G. Lecué, Probab. Theory Related Fields, 176, (2020), 897–940, arXiv:1810.01090.
  9. MONK -- Outlier-Robust Mean Embedding Estimation by Median-of-Means, with Zoltan Szabo, T. Mathieu and G. Lecué, (2019), ICML, PMLR 97:3782-3793, arXiv:1802.04784.
  10. Robust machine learning by median-of-means : theory and practice, with G. Lecué, Ann. Statist., 48, 2, (2020), 906-931, arXiv:1711.10306.
  11. Density estimation for RWRE, with A. Havet, E. Moulines, Math. Meth. Statist., 28, 1, (2019), 18-38, arXiv:1806.05839.
  12. Learning from MOM's principles : Le Cam's approach, with G. Lecué, Stoch. Proc. Appl, 129, 11, (2019), 4385-4410, arXiv:1701.01961.
  13. Non parametric estimation for random walks in random environment, with R. Diel, Stoch. Proc. Appl 128, 1 (2018) 132-155 arXiv:1606.03848.
  14. The number of potential winners in Bradley-Terry model in random environment, with R. Chetrite and R. Diel, Ann. Appl. Probab. 27, 3 (2017) 1372-1394 arXiv:1509.07265.
  15. Sub-Gaussian mean estimators, with L. Devroye, G. Lugosi and R. I. Oliveira, Ann. Statist. 44, 6 (2016) 2695--2725 arXiv:1509.05845.
  16. Family wise separation rates for multiple testing, with M. Fromont and P. Reynaud-Bouret, Ann. Statist., 44, 6 (2016) 2533-2563 hal-01107321v1.
  17. Parallel and pseudorandom discrete event system specification vs. networks of spiking neurons: Formalization and preliminary implementation results, with A. Muzy, F. Grammont, V.T. Dao and D.R.C. Hill, HPCS, Innsbruck, Austria, (2016).
  18. Optimal kernel selection for density estimation, with N. M. Magalhaes and P. Reynaud-Bouret, High dimensional probabilities VII: The Cargese Volume , volume 71 of Prog. Proba., Birkhauser (2016) 435--460 hal-01224097.
  19. Choice of V for V-fold cross-validation in least-squares density estimation, with S. Arlot, J. Mach. Learn. Res.; 17 (2016) (208):1--50, arXiv:1210.5830.
  20. Estimator Selection, Esaim Proc., 51 (2015) 232--245.
  21. Sharp oracle inequalities and slope heuristic for specification probabilities estimation in general random fields, with D.Y.Takahashi, Bernoulli, 22, 1 (2016) 325--344, arXiv:1106.2467.
  22. Markov approximation of chains of infinite order in the $\bar{d}$-metric, with S. Gallo and D.Y.Takahashi, Markov Process. Related Fields, 19 (2013) 51--82 arXiv:1107.4353.
  23. Kernels based tests with non-asymptotic bootstrap approaches for two-sample problem, with M. Fromont, B. Laurent and P. Reynaud-Bouret, COLT, 23 (2012) 23.1--23.23.
  24. An Oracle Approach for Interaction Neighborhood Estimation in Random Field, with D. Y. Takahashi, Electron. J. Stat., 5 (2011) 534--571, arXiv:1010.4783.
  25. Optimal model selection in density estimation, Ann. Inst. Henri Poincarré, 48, 3 (2012) 884--908, arXiv:0910.1654.
  26. Optimal model selection for density estimation of stationary data under various mixing conditions, Ann. Statist, 39, 1 (2011) 1852--1877 , arXiv:0911.1497.
  27. Adaptive non-asymptotic confidence balls in density estimation, ESAIM P&S, 16 (2012) 61--85, arXiv:1007.4528.
  28. Adaptive density estimation for stationary processes, Math. Meth. Statist. 18, 1 (2009) 59--83, arXiv:0909.0999.

Non publiés