Zobrazeno 1 - 10
of 33
pro vyhledávání: '"Matthieu Lerasle"'
We obtain risk bounds for Empirical Risk Minimizers (ERM) and minmax Median-Of-Means (MOM) estimators based on loss functions that are both Lipschitz and convex. Results for the ERM are derived without assumptions on the outputs and under subgaussian
Externí odkaz:
http://arxiv.org/abs/1810.01090
Autor:
Guillaume, Lecué, Matthieu, Lerasle
We obtain estimation error rates for estimators obtained by aggregation of regularized median-of-means tests, following a construction of Le Cam. The results hold with exponentially large probability -- as in the gaussian framework with independent n
Externí odkaz:
http://arxiv.org/abs/1701.01961
Autor:
Matthieu Lerasle, Guillaume Lecué
Publikováno v:
Annals of Statistics
Annals of Statistics, Institute of Mathematical Statistics, 2020, ⟨10.1214/19-AOS1828⟩
Ann. Statist. 48, no. 2 (2020), 906-931
Annals of Statistics, 2020, ⟨10.1214/19-AOS1828⟩
Annals of Statistics, Institute of Mathematical Statistics, 2020, ⟨10.1214/19-AOS1828⟩
Ann. Statist. 48, no. 2 (2020), 906-931
Annals of Statistics, 2020, ⟨10.1214/19-AOS1828⟩
We introduce new estimators for robust machine learning based on median-of-means (MOM) estimators of the mean of real valued random variables. These estimators achieve optimal rates of convergence under minimal assumptions on the dataset. The dataset
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::531780965edad7c90092e7ca46e091a2
https://hal.archives-ouvertes.fr/hal-01923036
https://hal.archives-ouvertes.fr/hal-01923036
Publikováno v:
Electronic Communications in Probability
Electronic Communications in Probability, Institute of Mathematical Statistics (IMS), 2020, 25, ⟨10.1214/20-ECP286⟩
Electron. Commun. Probab.
Electronic Communications in Probability, Institute of Mathematical Statistics (IMS), 2020, 25, ⟨10.1214/20-ECP286⟩
Electron. Commun. Probab.
We state and prove a quantitative version of the bounded difference inequality for geometrically ergodic Markov chains. Our proof uses the same martingale decomposition as \cite{MR3407208} but, compared to this paper, the exact coupling argument is m
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6cd6280a39cac0a77acd29858104a274
https://hal.archives-ouvertes.fr/hal-02473182
https://hal.archives-ouvertes.fr/hal-02473182
Publikováno v:
Bernoulli
Bernoulli, Bernoulli Society for Mathematical Statistics and Probability, 2020, 26 (4), pp.2670-2698. ⟨10.3150/20-BEJ1203⟩
Bernoulli 26, no. 4 (2020), 2670-2698
Bernoulli, Bernoulli Society for Mathematical Statistics and Probability, 2020, 26 (4), pp.2670-2698. ⟨10.3150/20-BEJ1203⟩
Bernoulli 26, no. 4 (2020), 2670-2698
International audience; Paired comparison data considered in this paper originate from the comparison of a large number N of individuals in couples. The dataset is a collection of results of contests between two individuals when each of them has face
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ca27b88f8a1b2812844bc9de7fb32a3a
https://hal.archives-ouvertes.fr/hal-03094519
https://hal.archives-ouvertes.fr/hal-03094519
Publikováno v:
Probability Theory and Related Fields
Probability Theory and Related Fields, Springer Verlag, 2019, ⟨10.1007/s00440-019-00931-3⟩
Probability Theory and Related Fields, 2019, ⟨10.1007/s00440-019-00931-3⟩
Probability Theory and Related Fields, Springer Verlag, 2019, ⟨10.1007/s00440-019-00931-3⟩
Probability Theory and Related Fields, 2019, ⟨10.1007/s00440-019-00931-3⟩
We obtain estimation and excess risk bounds for Empirical Risk Minimizers (ERM) and minmax Median-Of-Means (MOM) estimators based on loss functions that are both Lipschitz and convex. Results for the ERM are derived under weak assumptions on the outp
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::969e1edfbd3e9355708ee4dff2475f5c
https://hal.archives-ouvertes.fr/hal-01923033
https://hal.archives-ouvertes.fr/hal-01923033
Publikováno v:
Machine Learning. 109:1667-1667
There is a mistake in one of the authors’ names (in both online and print versions of the article): it should be Timothee Mathieu instead of Timlothee Mathieu.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7a57e4f98656aaebe6d9e97e6dae47ea
https://doi.org/10.1007/s10994-020-05885-5
https://doi.org/10.1007/s10994-020-05885-5
Publikováno v:
Electronic Journal of Statistics
Electronic Journal of Statistics, 2021, 15 (1), pp.1202-1227. ⟨10.1214/21-EJS1814⟩
Electronic Journal of Statistics, 2021, 15 (1), pp.1202-1227. ⟨10.1214/21-EJS1814⟩
Hyperparameters tuning and model selection are important steps in machine learning. Unfortunately, classical hyperparameter calibration and model selection procedures are sensitive to outliers and heavy-tailed data. In this work, we construct a selec
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5ff351a32b4f66f168446c84f6c17fe4
http://arxiv.org/abs/1812.02435
http://arxiv.org/abs/1812.02435
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
We consider the problem of nonparametric density estimation of a random environment from the observation of a single trajectory of a random walk in this environment. We build several density estimators using the beta-moments of this distribution. The
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c352b8001b1dbcc9d9118b412c4d4412