activity
20122023
most citedEntropic Ricci curvature bounds for discrete interacting systems

61 citations · 174 across the 27 of their papers we have counts for

collaborators

31 papers

math.PR2023

Transportation onto log-Lipschitz perturbations

Max Fathi, Dan Mikulincer, Yair Shenfeld

We establish sufficient conditions for the existence of globally Lipschitz transport maps between probability measures and their log-Lipschitz perturbations, with dimension-free bo…

math.MG2022★ 1 cited

Stability estimates for the sharp spectral gap bound under a curvature-dimension condition

Max Fathi, Ivan Gentil, Jordan Serres

We study stability of the sharp spectral gap bounds for metric-measure spaces satisfying a curvature bound. Our main result, new even in the smooth setting, is a sharp quantitative…

math.ST2021

Bounds in Wasserstein distance on the normal approximation of general M-estimators

François Bachoc, Max Fathi

We derive quantitative bounds on the rate of convergence in Wasserstein distance of general M-estimators, with an almost sharp (up to a logarithmic term) behavior in the numb…

math.MG2021

Stability of eigenvalues and observable diameter in RCD spaces

Jérôme Bertrand, Max Fathi

We study stability of the spectral gap and observable diameter for metricmeasure spaces satisfying the RCD(1, ) condition. We show that if such a space has an almost maxima…

math.PR2020★ 1 cited

Stability estimates for invariant measures of diffusion processes, with applications to stability of moment measures and Stein kernels

Max Fathi, Dan Mikulincer

We investigate stability of invariant measures of diffusion processes with respect to distances on the coefficients, under an assumption of log-concavity. The method is a var…

math.ST2020

Relaxing the Gaussian assumption in Shrinkage and SURE in high dimension

Max Fathi, Larry Goldstein, Gesine Reinert +1

Shrinkage estimation is a fundamental tool of modern statistics, pioneered by Charles Stein upon his discovery of the famous paradox involving the multivariate Gaussian. A large po…

math.FA2020

Self-improvement of the Bakry-Emery criterion for Poincar{é} inequalities and Wasserstein contraction using variable curvature bounds

Patrick Cattiaux, Max Fathi, Arnaud Guillin

We study Poincar{é} inequalities and long-time behavior for diffusion processes on R^n under a variable curvature lower bound, in the sense of Bakry-Emery. We derive various estima…

math.AP2019

Bounds on optimal transport maps onto log-concave measures

Maria Colombo, Max Fathi

We consider strictly log-concave measures, whose bounds degenerate at infinity. We prove that the optimal transport map from the Gaussian onto such a measure is locally Lipschitz,…

math.PR2019★ 8 cited

Entropic curvature and convergence to equilibrium for mean-field dynamics on discrete spaces

Matthias Erbar, Max Fathi, André Schlichting

We consider non-linear evolution equations arising from mean-field limits of particle systems on discrete spaces. We investigate a notion of curvature bounds for these dynamics bas…

math.PR2019★ 3 cited

A proof of the Caffarelli contraction theorem via entropic regularization

Max Fathi, Nathael Gozlan, Maxime Prodhomme

We give a new proof of the Caffarelli contraction theorem, which states that the Brenier optimal transport map sending the standard Gaussian measure onto a uniformly log-concave pr…

math.PR2018

Higher-order Stein kernels for Gaussian approximation

Max Fathi

We introduce higher-order Stein kernels relative to the standard Gaussian measure, which generalize the usual Stein kernels by involving higher-order derivatives of test functions.…

math.OA2018★ 1 cited

A note on existence of free Stein kernels

Guillaume Cébron, Max Fathi, Tobias Mai

Stein kernels are a way of comparing probability distributions, defined via integration by parts formulas. We provide two constructions of Stein kernels in free probability. One is…

math.FA2018★ 1 cited

Stability of the Bakry-Emery theorem on

Thomas A. Courtade, Max Fathi

We prove stability estimates for the Bakry-Emery bound on Poincaré and logarithmic Sobolev constants of uniformly log-concave measures. In particular, we improve the quantitative b…

math.PR2018

A sharp symmetrized form of Talagrand's transport-entropy inequality for the Gaussian measure

Max Fathi

This note presents a sharp transport-entropy inequality that improves on Talagrand's inequality for the Gaussian measure, arising as a dual formulation of the functional Santaló in…

math.PR2018★ 45 cited

Stein kernels and moment maps

Max Fathi

We describe a construction of Stein kernels using moment maps, which are solutions to a variant of the Monge-Ampère equation. As a consequence, we show how regularity bounds on the…

math.PR2017★ 3 cited

Existence of Stein Kernels under a Spectral Gap, and Discrepancy Bound

Thomas A. Courtade, Max Fathi, Ashwin Pananjady

We establish existence of Stein kernels for probability measures on satisfying a Poincaré inequality, and obtain bounds on the Stein discrepancy of such measures. Ap…

math.PR2016

Poincaré, modified logarithmic Sobolev and isoperimetric inequalities for Markov chains with non-negative Ricci curvature

Matthias Erbar, Max Fathi

We study functional inequalities for Markov chains on discrete spaces with entropic Ricci curvature bounded from below. Our main results are that when curvature is non-negative, bu…

cs.IT2016★ 11 cited

Wasserstein Stability of the Entropy Power Inequality for Log-Concave Densities

Thomas A. Courtade, Max Fathi, Ashwin Pananjady

We establish quantitative stability results for the entropy power inequality (EPI). Specifically, we show that if uniformly log-concave densities nearly saturate the EPI, then they…

math.OA2016

Free Stein kernels and an improvement of the free logarithmic Sobolev inequality

Max Fathi, Brent Nelson

We introduce a free version of the Stein kernel, relative to a semicircular law. We use it to obtain a free counterpart of the HSI inequality of Ledoux, Peccatti and Nourdin, which…

math.PR2016★ 32 cited

Gradient flow structure for McKean-Vlasov equations on discrete spaces

Matthias Erbar, Max Fathi, Vaios Laschos +1

In this work, we show that a family of non-linear mean-field equations on discrete spaces can be viewed as a gradient flow of a natural free energy functional with respect to a cer…

math.PR2015

Curvature and transport inequalities for Markov chains in discrete spaces

Max Fathi, Yan Shu

We study various transport-information inequalities under three different notions of Ricci curvature in the discrete setting: the curvature-dimension condition of Bakry and Émery,…

math.PR2015★ 1 cited

The gradient flow approach to hydrodynamic limits for the simple exclusion process

Max Fathi, Marielle Simon

We give a new approach to the well-known convergence to the hydrodynamic limit for the symmetric simple exclusion process (SSEP). More precisely, we characterize any possible limit…

math.PR2015★ 61 cited

Entropic Ricci curvature bounds for discrete interacting systems

Max Fathi, Jan Maas

We develop a new and systematic method for proving entropic Ricci curvature lower bounds for Markov chains on discrete sets. Using different methods, such bounds have recently been…

math.PR2014

Quantitative logarithmic Sobolev inequalities and stability estimates

Max Fathi, Emanuel Indrei, Michel Ledoux

We establish an improved form of the classical logarithmic Sobolev inequality for the Gaussian measure restricted to probability densities which satisfy a Poincaré inequality. The…