Research Interest:

Brief Bio:

Rodrigo Maulen-Soto received his Mathematical Engineer's degree and his M.Sc. in Applied Mathematics in 2021 from Universidad de Chile, Chile. During his Master he worked under the supervision of Juan Peypouquet and Guillaume Garrigos, where his main topic of research was on the line of continuous time models for modeling Stochastic Gradient Descent. The same year he moved to Caen, France, where he started his Ph.D. under the supervision of Jalal Fadili, Peter Ochs and collaborating with Hedy Attouch. This Ph.D. position arises from the TRINOM-DS project and focuses mainly on continuous stochastic systems for solving convex optimization problems in Hilbert spaces, where Stochastic Differential Equations govern the dynamics. The goal is to give conditions on the objective function and the noise to ensure almost sure weak convergence of the trajectories to the set of minimizers. This led to the proposal of stochastic counterparts to Gradient Flow and the Inertial System with Implicit Hessian Damping. His research interests lie in the field of Optimization and Stochastic Systems. In general, he is motivated by the theoretical analysis of applied problems that arise from Machine Learning.