5 papers
PPO in the Fisher-Rao geometry
Razvan-Andrei Lascu, David Šiška, Łukasz Szpruch
Proximal Policy Optimization (PPO) is widely used in reinforcement learning due to its strong empirical performance, yet it lacks formal guarantees for policy improvement and conve…
Linear convergence of proximal descent schemes on the Wasserstein space
Razvan-Andrei Lascu, Mateusz B. Majka, David Šiška +1
We investigate proximal descent methods, inspired by the minimizing movement scheme introduced by Jordan, Kinderlehrer and Otto, for optimizing entropy-regularized functionals on t…
A Fisher-Rao gradient flow for entropic mean-field min-max games
Razvan-Andrei Lascu, Mateusz B. Majka, Łukasz Szpruch
Gradient flows play a substantial role in addressing many machine learning problems. We examine the convergence in continuous-time of a \textit{Fisher-Rao} (Mean-Field Birth-Death)…
Mirror Descent-Ascent for mean-field min-max problems
Razvan-Andrei Lascu, Mateusz B. Majka, Łukasz Szpruch
We study two variants of the mirror descent-ascent (MDA) algorithm for solving min-max problems on the space of measures: simultaneous and alternating. We work under assumptions of…
Non-asymptotic bounds for sampling algorithms without log-concavity
Mateusz B. Majka, Aleksandar Mijatović, Lukasz Szpruch
Discrete time analogues of ergodic stochastic differential equations (SDEs) are one of the most popular and flexible tools for sampling high-dimensional probability measures. Non-a…