activity
20182026
most citedInfinite-width limit of deep linear neural networks

5 citations · 7 across the 5 of their papers we have counts for

collaborators

11 papers

math.AP2026

Bellman Equations with Sub-Lipschitz Hessians

Xavier Fernández-Real

We construct homogeneous solutions with non-Lipschitz Hessian for finite, constant-coefficient Bellman equations. First, for every , we find two uniformly elliptic matri…

math.AP2023

Generic properties in free boundary problems

Xavier Fernández-Real, Hui Yu

In this work, we show the generic uniqueness of minimizers for a large class of energies, including the Alt-Caffarelli and Alt-Phillips functionals. We then prove the generic regul…

math.AP2023

Schauder and Cordes-Nirenberg estimates for nonlocal elliptic equations with singular kernels

Xavier Fernández-Real, Xavier Ros-Oton

We study integro-differential elliptic equations (of order ) with variable coefficients, and prove the natural and most general Schauder-type estimates that can hold in this se…

math.AP20232 cited

Smooth approximations for fully nonlinear nonlocal elliptic equations

Xavier Fernández-Real

We show that any viscosity solution to a general fully nonlinear nonlocal elliptic equation can be approximated by smooth () solutions.

cs.LG20225 cited

Infinite-width limit of deep linear neural networks

Lénaïc Chizat, Maria Colombo, Xavier Fernández-Real +1

This paper studies the infinite-width limit of deep linear neural networks initialized with random parameters. We obtain that, when the number of neurons diverges, the training dyn…

math.AP2021

Improved regularity of second derivatives for subharmonic functions

Xavier Fernández-Real, Riccardo Tione

In this note, we prove that if a subharmonic function has pure second derivatives that are signed measures, then their negative part $(\partial_{ii} u)_…