128 citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Toulouse School of EconomicsFR17 papers
- Université de ToulouseFR11 papers
- Institut de Recherche en Informatique de ToulouseFR9 papers
- Université Toulouse III - Paul SabatierFR8 papers
- Université Toulouse-I-CapitoleFR7 papers
- Institut Polytechnique de BordeauxFR5 papers
- Université Toulouse - Jean JaurèsFR5 papers
- Institut de Mathématiques de ToulouseFR4 papers
- Université Fédérale de Toulouse Midi-PyrénéesFR4 papers
- Université Toulouse CapitoleFR4 papers
- Centre National de la Recherche ScientifiqueFR3 papers
- Technology Solutions Experts (United States)US3 papers
5 papers · 1 filter
Differentiating Nonsmooth Solutions to Parametric Monotone Inclusion Problems
Jérôme Bolte, Edouard Pauwels, Antonio Silveti-Falls
We leverage path differentiability and a recent result on nonsmooth implicit differentiation calculus to give sufficient conditions ensuring that the solution to a monotone inclusi…
Numerical influence of ReLU'(0) on backpropagation
David Bertoin, Jérôme Bolte, Sébastien Gerchinovitz +1
In theory, the choice of ReLU(0) in [0, 1] for a neural network has a negligible influence both on backpropagation and training. Yet, in the real world, 32 bits default precision c…
Second-order step-size tuning of SGD for non-convex optimization
Camille Castera, Jérôme Bolte, Cédric Févotte +1
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…
ROI Maximization in Stochastic Online Decision-Making
Nicolò Cesa-Bianchi, Tommaso Cesari, Yishay Mansour +1
We introduce a novel theoretical framework for Return On Investment (ROI) maximization in repeated decision-making. Our setting is motivated by the use case of companies that regul…
Cooperative Online Learning: Keeping your Neighbors Updated
Nicolò Cesa-Bianchi, Tommaso R. Cesari, Claire Monteleoni
We study an asynchronous online learning setting with a network of agents. At each time step, some of the agents are activated, requested to make a prediction, and pay the correspo…