Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Sébastien Gerchinovitz"'
Autor:
Florence de Grancey, Jean-Luc Adam, Lucian Alecu, Sébastien Gerchinovitz, Franck Mamalet, David Vigouroux
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031148613
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3849ebe7a5cd541a74bac3fb369af643
https://doi.org/10.1007/978-3-031-14862-0_23
https://doi.org/10.1007/978-3-031-14862-0_23
Publikováno v:
AISTATS 2021
AISTATS 2021, Apr 2021, virtual, United States. pp.424-432
HAL
AISTATS 2021, Apr 2021, virtual, United States. pp.424-432
HAL
International audience; We study the problem of approximating the level set of an unknown function by sequentially querying its values. We introduce a family of algorithms called Bisect and Approximate through which we reduce the level set approximat
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e06b9f31a1e3d1bc1ab6fa026b05e49f
https://hal.archives-ouvertes.fr/hal-02976018v2/document
https://hal.archives-ouvertes.fr/hal-02976018v2/document
Publikováno v:
Statist. Sci. 35, no. 2 (2020), 178-201
We extend Fano's inequality, which controls the average probability of (disjoint) events in terms of the average of some Kullback-Leibler divergences, to work with arbitrary [0,1]-valued random variables. Our simple two-step methodology is general en
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6bc565f39619111192faaf17819dd6d3
https://projecteuclid.org/euclid.ss/1591171226
https://projecteuclid.org/euclid.ss/1591171226
Autor:
Aurélien Garivier, Nicolas Grislain, Pascal Dkengne Sielenou, Sébastien Gerchinovitz, Grégoire Jauvion
Publikováno v:
The 24th ACM SIGKDD International Conference on Knowledge Discovery \& Data Mining
The 24th ACM SIGKDD International Conference on Knowledge Discovery \& Data Mining, Aug 2018, London, United Kingdom. ⟨10.1145/3219819.3219917⟩
KDD
The 24th ACM SIGKDD International Conference on Knowledge Discovery \& Data Mining, Aug 2018, London, United Kingdom. ⟨10.1145/3219819.3219917⟩
KDD
International audience; Over the last decade, digital media (web or app publishers) generalized the use of real time ad auctions to sell their ad spaces. Multiple auction platforms, also called Supply-Side Platforms (SSP), were created. Because of th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a2d5800b310c297aa902ba85366c8d4f
https://hal.archives-ouvertes.fr/hal-01822524/file/header_bidding.pdf
https://hal.archives-ouvertes.fr/hal-01822524/file/header_bidding.pdf
Publikováno v:
Bernoulli 26, no. 3 (2020), 1797-1831
Bernoulli
Bernoulli, Bernoulli Society for Mathematical Statistics and Probability, 2020, 26 (3), pp.1797-1831. ⟨10.3150/19-BEJ1170⟩
Bernoulli, 2020, 26 (3), pp.1797-1831. ⟨10.3150/19-BEJ1170⟩
Bernoulli
Bernoulli, Bernoulli Society for Mathematical Statistics and Probability, 2020, 26 (3), pp.1797-1831. ⟨10.3150/19-BEJ1170⟩
Bernoulli, 2020, 26 (3), pp.1797-1831. ⟨10.3150/19-BEJ1170⟩
We consider the binary supervised classification problem with the Gaussian functional model introduced in (Math. Methods Statist. 22 (2013) 213–225). Taking advantage of the Gaussian structure, we design a natural plug-in classifier and derive a fa
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8e963632218c3c53fffcacad779ac869
http://tse-fr.eu/pub/32574
http://tse-fr.eu/pub/32574
Autor:
Sébastien Gerchinovitz, Jia Yuan Yu
Publikováno v:
Theoretical Computer Science. 519:4-28
We consider the problem of online linear regression on individual sequences. The goal in this paper is for the forecaster to output sequential predictions which are, after T time rounds, almost as good as the ones output by the best linear predictor
Autor:
Clément Bouttier, Sébastien Gadat, Sebastien Laporte, Florence Nicol, Sébastien Gerchinovitz, Olivier Babando
Publikováno v:
International Conference of the German, Austrian and Swiss Operations Research Societies (GOR, ÖGOR, SVOR/ASRO
International Conference of the German, Austrian and Swiss Operations Research Societies (GOR, ÖGOR, SVOR/ASRO, Sep 2015, Vienne, Austria. pp 569-574, ⟨10.1007/978-3-319-42902-1_77⟩
Operations Research Proceedings ISBN: 9783319429014
OR
International Conference of the German, Austrian and Swiss Operations Research Societies (GOR, ÖGOR, SVOR/ASRO, Sep 2015, Vienne, Austria. pp 569-574, ⟨10.1007/978-3-319-42902-1_77⟩
Operations Research Proceedings ISBN: 9783319429014
OR
International audience; In air traffic management, most optimization procedures are commonly based on deterministic modeling and do not take into account the uncertainties on environmental conditions (e.g., wind) and on air traffic control operations
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::eff759a339a5d508c775e66698f4c0c9
https://hal-enac.archives-ouvertes.fr/hal-01575800
https://hal-enac.archives-ouvertes.fr/hal-01575800
Autor:
Achour, El Mehdi
Publikováno v:
Optimisation et contrôle [math.OC]. Université Paul Sabatier-Toulouse III, 2022. Français. ⟨NNT : 2022TOU30202⟩
In this thesis, we study different theoretical aspects of deep learning, in particular optimization, robustness, and approximation. Optimization: We study the optimization landscape of the empirical risk of deep linear neural networks with the square
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od______4074::0b1fec299ad06985d6144c29c9798f10
https://theses.hal.science/tel-04122195/file/2022TOU30202b.pdf
https://theses.hal.science/tel-04122195/file/2022TOU30202b.pdf