Taming the Interactive Particle Langevin Algorithm -- the superlinear case

arXiv:2403.19587v1 Announce Type: cross
Abstract: Recent advances in stochastic optimization have yielded the interactive particle Langevin algorithm (IPLA), which leverages the notion of interacting particle systems (IPS) to efficiently sample from approximate posterior densities. This becomes particularly crucial within the framework of Expectation-Maximization (EM), where the E-step is computationally challenging or even intractable. Although prior research has focused on scenarios involving convex cases with gradients of log densities that grow at most linearly, our work extends this framework to include …

abstract advances algorithm arxiv case expectation-maximization framework interactive math.pr notion optimization particle posterior sample stat.co stat.ml stochastic systems type