97 citations
- Laboratoire de Probabilités et Modèles AléatoiresFR238 papers
- Sorbonne UniversitéFR182 papers
- Centre National de la Recherche ScientifiqueFR143 papers
- Université Paris CitéFR90 papers
- Sorbonne Paris CitéFR46 papers
- Centre de Mathématiques Appliquées de l'École polytechniqueFR29 papers
- École Normale Supérieure - PSLFR28 papers
- Laboratoire de Mathématiques d'OrsayFR28 papers
- Département de mathématiques et applicationsFR25 papers
- École PolytechniqueFR24 papers
- Institut Universitaire de FranceFR23 papers
- Université Paris DiderotFR23 papers
541 papers
Polyak-Łojasiewicz inequality is essentially no more general than strong convexity for functions
Aziz Ben Nejma
The Polyak-Łojasiewicz (PŁ) inequality extends the favorable optimization properties of strongly convex functions to a broader class of functions. In this paper, we prove a theorem…
Strong zero modes in integrable spin-S chains
Fabian H. L. Essler, Paul Fendley, Eric Vernier
We derive exact strong zero mode (ESZM) operators for integrable spin-S chains with open boundary conditions and a boundary field. Their locality properties are generally weaker th…
Quantitative rigidity of the Wasserstein contraction under convolution
Max Fathi, Michael Goldman, Daniel Tsodyks
The aim of this paper is to investigate the contraction properties of -Wasserstein distances with respect to convolution in Euclidean spaces both qualitatively and quantitativel…
Fairness Meets Privacy: Integrating Differential Privacy and Demographic Parity in Multi-class Classification
Lilian Say, Christophe Denis, Rafael Pinot
The increasing use of machine learning in sensitive applications demands algorithms that simultaneously preserve data privacy and ensure fairness across potentially sensitive sub-p…
Maxitive Donsker-Varadhan Formulation for Possibilistic Variational Inference
Jasraj Singh, Shelvia Wongso, Jeremie Houssineau +1
Variational inference (VI) is a cornerstone of modern Bayesian learning, enabling approximate inference in complex models. However, its formulation depends on expectations and dive…
Harmonic functions on Tutte embeddings and linearized Monge-Ampère equation
Mikhail Basok, Dmitry Chelkak, Benoît Laslier +1
We prove convergence of solutions of Dirichlet problems and Green's functions on Tutte harmonic embeddings to those of the linearized Monge--Ampère equation . Mor…