10.6k citations
- Laboratoire Traitement et Communication de l’InformationFR516 papers
- Centre National de la Recherche ScientifiqueFR357 papers
- ParisTechFR221 papers
- Université Paris-SudFR118 papers
- Institut Polytechnique de ParisFR115 papers
- Université Paris-SaclayFR114 papers
- University of California, BerkeleyUS114 papers
- University of TorontoCA110 papers
- Imperial College LondonGB109 papers
- Sapienza University of RomeIT109 papers
- University of CambridgeGB109 papers
- California Institute of TechnologyUS108 papers
5 papers · 2 filters
Phase Diagram of Dropout for Two-Layer Neural Networks in the Mean-Field Regime
Lénaïc Chizat, Pierre Marion, Yerkin Yesbay
Dropout is a standard training technique for neural networks that consists of randomly deactivating units at each step of their gradient-based training. It is known to improve perf…
From the Gradient-Step Denoiser to the Proximal Denoiser and their associated convergent Plug-and-Play algorithms
Vincent Herfeld, Baudouin Denis de Senneville, Arthur Leclaire +1
In this paper we analyze the Gradient-Step Denoiser and its usage in Plug-and-Play algorithms. The Plug-and-Play paradigm of optimization algorithms uses off the shelf denoisers to…
To Each Metric Its Decoding: Post-Hoc Optimal Decision Rules of Probabilistic Hierarchical Classifiers
Roman Plaud, Alexandre Perez-Lebel, Matthieu Labeau +2
Hierarchical classification offers an approach to incorporate the concept of mistake severity by leveraging a structured, labeled hierarchy. However, decoding in such settings freq…
Fair Text Classification via Transferable Representations
Thibaud Leteno, Michael Perrot, Charlotte Laclau +2
Group fairness is a central research topic in text classification, where reaching fair treatment between sensitive groups (e.g., women and men) remains an open challenge. We propos…
Differentially Private Policy Gradient
Alexandre Rio, Merwan Barlier, Igor Colin
Motivated by the increasing deployment of reinforcement learning in the real world, involving a large consumption of personal data, we introduce a differentially private (DP) polic…