Ito Diffusion Approximation of Universal Ito Chains for Sampling, Optimization and Boosting

arXiv:2310.06081v2 Announce Type: replace-cross
Abstract: In this work, we consider rather general and broad class of Markov chains, Ito chains, that look like Euler-Maryama discretization of some Stochastic Differential Equation. The chain we study is a unified framework for theoretical analysis. It comes with almost arbitrary isotropic and state-dependent noise instead of normal and state-independent one as in most related papers. Moreover, in our chain the drift and diffusion coefficient can be inexact in order to cover wide range of …

abstract analysis approximation arxiv boosting class cs.lg differential differential equation diffusion equation framework general ito look markov math.oc math.pr optimization sampling stat.ml stochastic study type universal work