DMA Health Strategies

output

20042026

most citedGeometric Losses for Distributional Learning

3 citations

researchers with a paper here

collaborating institutions

28 papers

cs.LG2026

Gaussian Flow-Matching Schedules: Implications for Sampling and Training

Arsène Claustre, Hugo Negrel, Claire Boyer +2

Flow-matching schedules affect both sampling dynamics and the variance of the regression target. For centered commuting Gaussians, we show that a direction-dependent schedule decom…

math.AP2025

Nonlinear Forward-Backward Problems

Anne-Laure Dalibard, Frédéric Marbach, Jean Rax

We prove the existence and uniqueness of strong solutions to the equation $u u_{x} - u_{y y} = f$ in the vicinity of the linear shear flow, subject to perturbations of the source term…

math.AP2024

Profile decomposition and scattering for general nonlinear Schr{ö}dinger equations

Thomas Duyckaerts, Phan van Tin

We consider a Schr{ö}dinger equation with a nonlinearity which is a general perturbation of a power'' nonlinearity. We construct a profile decomposition adapted to this nonlinearit…

math.FA2023

Perron's capacity of random sets

Anthony Gauvan

Given a sequence of random variables ${X_{k} : k \geq 1}$ uniformly distributed in $(0, 1)$ and independent, we consider the following random sets of directions $$Ω_{\te…

math.FA2023

A family of interpolation inequalities involving products of low-order derivatives

Frédéric Marbach

Gagliardo-Nirenberg interpolation inequalities relate Lebesgue norms of iterated derivatives of a function. We present a generalization of these inequalities in which the low-order…

math.CA2023

Maximal operators on hyperbolic triangles

Anthony Gauvan, Samuel Bronstein, Romain Branchereau

We characterize the boundedness properties on the spaces $L^{p} (H^{2})$ of the maximal operator $M_{B}$ where $B$ is an arbitrary family of hyperbolic triang…