Zobrazeno 1 - 10
of 241
pro vyhledávání: '"Chrétien, Stéphane"'
Anomaly detection in multivariate signals is a task of paramount importance in many disciplines (epidemiology, finance, cognitive sciences and neurosciences, oncology, etc.). In this perspective, Topological Data Analysis (TDA) offers a battery of "s
Externí odkaz:
http://arxiv.org/abs/2404.15328
Hardware implementation of neural network are an essential step to implement next generation efficient and powerful artificial intelligence solutions. Besides the realization of a parallel, efficient and scalable hardware architecture, the optimizati
Externí odkaz:
http://arxiv.org/abs/2305.07908
This work addresses the Robust counterpart of the Shortest Path Problem (RSPP) with a correlated uncertainty set. Since this problem is hard, a heuristic approach, based on Frank-Wolfe's algorithm named Discrete Frank-Wolf (DFW), has recently been pr
Externí odkaz:
http://arxiv.org/abs/2110.15653
Autor:
Caron, Emmanuel, Chretien, Stephane
Recent extensive numerical experiments in high scale machine learning have allowed to uncover a quite counterintuitive phase transition, as a function of the ratio between the sample size and the number of parameters in the model. As the number of pa
Externí odkaz:
http://arxiv.org/abs/2007.12882
We study the problem of super-resolution, where we recover the locations and weights of non-negative point sources from a few samples of their convolution with a Gaussian kernel. It has been shown that exact recovery is possible by minimising the tot
Externí odkaz:
http://arxiv.org/abs/2007.02708
Many statistical learning problems have recently been shown to be amenable to Semi-Definite Programming (SDP), with community detection and clustering in Gaussian mixture models as the most striking instances [javanmard et al., 2016]. Given the growi
Externí odkaz:
http://arxiv.org/abs/2004.01869
Autor:
Andreoli, Louis, Porte, Xavier, Chrétien, Stéphane, Jacquot, Maxime, Larger, Laurent, Brunner, Daniel
Publikováno v:
Nanophotonics (published online ahead of print), 20200171 (2020)
A high efficiency hardware integration of neural networks benefits from realizing nonlinearity, network connectivity and learning fully in a physical substrate. Multiple systems have recently implemented some or all of these operations, yet the focus
Externí odkaz:
http://arxiv.org/abs/2003.12319
Autor:
Chrétien, Stéphane1, Kammoun, Manel2 manel.kammoun@uqo.ca
Publikováno v:
Financial Services Review. 2024, Vol. 32 Issue 1, p63-94. 32p.
Autor:
Chrétien, Stéphane, Fu, Hsuan
Publikováno v:
In Finance Research Letters May 2023 53
We study the problem of super-resolution, where we recover the locations and weights of non-negative point sources from a few samples of their convolution with a Gaussian kernel. It has been recently shown that exact recovery is possible by minimisin
Externí odkaz:
http://arxiv.org/abs/1904.01926