Zobrazeno 1 - 10
of 37
pro vyhledávání: '"Edouard Pauwels"'
Autor:
Edouard Pauwels, Didier Surdez, Gautier Stoll, Aurianne Lescure, Elaine Del Nery, Olivier Delattre, Véronique Stoven
Publikováno v:
PLoS ONE, Vol 7, Iss 8, p e42715 (2012)
High Content Screening (HCS) platforms allow screening living cells under a wide range of experimental conditions and give access to a whole panel of cellular responses to a specific treatment. The outcome is a series of cell population images. Withi
Externí odkaz:
https://doaj.org/article/dd89a1846ccc47a3ba049ec3c745a655
The Christoffel–Darboux kernel, a central object in approximation theory, is shown to have many potential uses in modern data analysis, including applications in machine learning. This is the first book to offer a rapid introduction to the subject,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::cea111c92f8842dd3d56c546fd9af72d
https://doi.org/10.1017/9781108937078
https://doi.org/10.1017/9781108937078
Publikováno v:
ESAIM: Probability and Statistics
ESAIM: Probability and Statistics, EDP Sciences, 2022, ⟨10.1051/ps/2022003⟩
ESAIM: Probability and Statistics, 2022, 26, pp.171-207. ⟨10.1051/ps/2022003⟩
ESAIM: Probability and Statistics, EDP Sciences, 2022, ⟨10.1051/ps/2022003⟩
ESAIM: Probability and Statistics, 2022, 26, pp.171-207. ⟨10.1051/ps/2022003⟩
International audience; We consider the problem of estimating the support of a measure from a finite, independent, sample. The estimators which are considered are constructed based on the empirical Christoffel function. Such estimators have been prop
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f49718a9f1ec8b908440bb727070a6c6
https://hal.archives-ouvertes.fr/hal-02940479
https://hal.archives-ouvertes.fr/hal-02940479
Autor:
Swann Marx, Edouard Pauwels
Publikováno v:
Journal of Differential Equations
Journal of Differential Equations, 2022
Journal of Differential Equations, 2022
International audience; We consider flows of ordinary differential equations (ODEs) driven by path differentiable vector fields. Path differentiable functions constitute a proper subclass of Lipschitz functions which admit conservative gradients, a n
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::dc452fe1f686bf3c904fc1eef398104a
Publikováno v:
Computational Optimization and Applications
Computational Optimization and Applications, 2022, 81 (1), pp.31-66. ⟨10.1007/s10589-021-00325-z⟩
Computational Optimization and Applications, Springer Verlag, 2021, ⟨10.1007/s10589-021-00325-z⟩
Computational Optimization and Applications, 2022, 81 (1), pp.31-66. ⟨10.1007/s10589-021-00325-z⟩
Computational Optimization and Applications, Springer Verlag, 2021, ⟨10.1007/s10589-021-00325-z⟩
We introduce a sublevel Moment-SOS hierarchy where each SDP relaxation can be viewed as an intermediate (or interpolation) between the d-th and (d+1)-th order SDP relaxations of the Moment-SOS hierarchy (dense or sparse version). With the flexible ch
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::12d2bbb26cb478e7b49609cfea74b356
https://hal.laas.fr/hal-03109978
https://hal.laas.fr/hal-03109978
Publikováno v:
Constructive Approximation
Constructive Approximation, 2021, 54 (3), pp.391-429. ⟨10.1007/s00365-021-09535-4⟩
Constructive Approximation, Springer Verlag, 2021, 54 (3), pp.391-429. ⟨10.1007/s00365-021-09535-4⟩
Constructive Approximation, 2021, 54 (3), pp.391-429. ⟨10.1007/s00365-021-09535-4⟩
Constructive Approximation, Springer Verlag, 2021, 54 (3), pp.391-429. ⟨10.1007/s00365-021-09535-4⟩
International audience; We provide a new method to approximate a (possibly discontinuous) function using Christoffel-Darboux kernels. Our knowledge about the unknown multivariate function is in terms of finitely many moments of the Young measure supp
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::219ff0e236cd58484dfc1b67a5ac0eee
https://hal.science/hal-02085835v3/document
https://hal.science/hal-02085835v3/document
Publikováno v:
HAL
In view of training increasingly complex learning architectures, we establish a nonsmooth implicit function theorem with an operational calculus. Our result applies to most practical problems (i.e., definable problems) provided that a nonsmooth form
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::654877d6a0514f4515bdf68efb528d3e
http://arxiv.org/abs/2106.04350
http://arxiv.org/abs/2106.04350
Publikováno v:
Neural Processing Letters
Neural Processing Letters, 2022, pp.1--26. ⟨10.1007/s11063-021-10705-5⟩
Neural Processing Letters, 2022, pp.1--26. ⟨10.1007/s11063-021-10705-5⟩
In view of a direct and simple improvement of vanilla SGD, this paper presents a fine-tuning of its step-sizes in the mini-batch case. For doing so, one estimates curvature, based on a local quadratic model and using only noisy gradient approximation
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4d1af568f532fdf8b4cd6d480d37876d
Autor:
Cheik Traoré, Edouard Pauwels
Publikováno v:
Operations Research Letters
We prove that the iterates produced by, either the scalar step size variant, or the coordinatewise variant of AdaGrad algorithm, are convergent sequences when applied to convex objective functions with Lipschitz gradient. The key insight is to remark
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::faf70daaf17836bd9ee9c3fef3b825d3
http://arxiv.org/abs/2011.12341
http://arxiv.org/abs/2011.12341
Autor:
Edouard Pauwels, Jérôme Bolte
Publikováno v:
Mathematical Programming
Mathematical Programming, Springer Verlag, 2020, ⟨10.1007/s10107-020-01501-5⟩
Mathematical Programming, Springer Verlag, 2020, ⟨10.1007/s10107-020-01501-5⟩
Modern problems in AI or in numerical analysis require nonsmooth approaches with a flexible calculus. We introduce generalized derivatives called conservative fields for which we develop a calculus and provide representation formulas. Functions havin
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::465db867d603ae99fd8fb6f1f007bff7
https://hal.archives-ouvertes.fr/hal-02521848
https://hal.archives-ouvertes.fr/hal-02521848