activity
20242026
collaborators

5 papers

cs.LG2026

Universal Approximation of Nonlinear Operators and Their Derivatives

Filippo de Feo

Establishing Universal Approximation Theorems (UATs) for nonlinear operators and their derivatives is a foundational open problem in Operator Learning (OL) and raises delicate ques…

math.PR2025

Stochastic Optimal Control of Interacting Particle Systems in Hilbert Spaces and Applications

Filippo de Feo, Fausto Gozzi, Andrzej Święch +1

Optimal control of interacting particles governed by stochastic evolution equations in Hilbert spaces is an open area of research. Such systems naturally arise in formulations wher…

math.PR2025

Sensitivity of functionals of McKean-Vlasov SDE's with respect to the initial distribution

Filippo de Feo, Salvatore Federico, Fausto Gozzi +1

We examine the sensitivity at the origin of the distributional robust optimization problem in the context of a model generated by a mean field stochastic differential equation. We…

math.OC2025

Stochastic optimal control in Hilbert spaces: regularity of the value function and optimal synthesis via viscosity solutions

Filippo de Feo, Andrzej Święch, Lukas Wessels

We study optimal control problems governed by abstract infinite dimensional stochastic differential equations using the dynamic programming approach. In the first part, we prove Li…

math.OC2024

Optimal control of stochastic delay differential equations: Optimal feedback controls

Filippo de Feo, Andrzej Święch

In this manuscript, we study optimal control problems for stochastic delay differential equations using the dynamic programming approach in Hilbert spaces via viscosity solutions o…