activity
20242026
collaborators

8 papers

math.OC2026

Mean-Field PhiBE: Continuous-Time Mean-Field Reinforcement Learning from Discrete-Time Data

Erhan Bayraktar, Martin Hernandez, Qinxin Yan +1

This paper addresses model-free continuous-time mean-field control in a setting where the population dynamics evolve continuously according to an unknown McKean-Vlasov stochastic d…

math.OC2026

Policy Gradient for Continuous-Time Mean-Field Control

Erhan Bayraktar, Martin Hernandez, Qinxin Yan +1

This paper develops a policy gradient method for entropy-regularized mean-field control in the discounted infinite-horizon setting. We consider randomized feedback policies and a c…

cs.LG2025

Convergence, design and training of continuous-time dropout as a random batch method

Antonio Álvarez-López, Martín Hernández

We study dropout regularization in continuous-time models through the lens of random-batch methods -- a family of stochastic sampling schemes originally devised to reduce the compu…

math.NA2025

Random domain decomposition for parabolic PDEs on graphs

Martín Hernández

The simulation of complex systems, such as gas transport in large pipeline networks, often involves solving PDEs posed on intricate graph structures. Such problems require consider…

stat.ML2025

Constructive Universal Approximation and Finite Sample Memorization by Narrow Deep ReLU Networks

Martín Hernández, Enrique Zuazua

We present a fully constructive analysis of deep ReLU neural networks for classification and function approximation tasks. First, we prove that any dataset with distinct points…

math.NA2025

Random Batch Methods for Discretized PDEs on Graphs

Martín Hernández, Enrique Zuazua

Gas transport and other complex real-world challenges often require solving and controlling partial differential equations (PDEs) defined on graph structures, which typically deman…