output
20052026
most citedHow to estimate carbon footprint when training deep learning models? A guide and review

120 citations

researchers with a paper here
collaborating institutions
Showing math.FAShow all

8 papers · 1 filter

math.FA2026

A Brenier-Strassen Theorem on CAT(kappa) Spaces

Nathael Gozlan, Hugo Malamut, Shin-Ichi Ohta

We extend the Brenier-Strassen theorem about projections in convex order to non-flat spaces with curvature bounded from above. Precisely, for probability measures , of finit…

math.FA2025

On the quadratic barycentric transport problem

Nathael Gozlan, Thibaut Le Gouic, Paul-Marie Samson

We investigate the structure of optimal transport plans, dual optimizers, and geodesic paths for the quadratic barycentric transport problem.

math.FA2025

Explicit Universal and Approximate-Universal Kernels on Compact Metric Spaces

Eloi Tanguy

Universal kernels, whose Reproducing Kernel Hilbert Space is dense in the space of continuous functions are of great practical and theoretical interest. In this paper, we introduce…

math.FA2025

Global Regularity Estimates for Optimal Transport via Entropic Regularisation

Nathael Gozlan, Maxime Sylvestre

We develop a general approach to prove global regularity estimates for quadratic optimal transport using the entropic regularisation of the problem and the Prekopa-Leindler inequal…

math.FA2024

Some obstructions to contraction theorems on the half-sphere

Max Fathi, Matthieu Fradelizi, Nathael Gozlan +1

Caffarelli's contraction theorem states that probability measures with uniformly logconcave densities on R d can be realized as the image of a standard Gaussian measure by a global…

math.FA2023

Transport-entropy forms of direct and Converseblaschke-Santal{ó} inequalities

Matthieu Fradelizi, Nathael Gozlan, Shay Sadovsky +1

We explore alternative functional or transport-entropy formulations of the Blaschke-Santal{ó} inequality and of its conjectured counterpart due to Mahler. In particular, we obtain…