Saved in:
Bibliographic Details
Main Authors: Benko, Matej, Chlebicka, Iwona, Endal, Jørgen, Miasojedow, Błażej
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2412.09698
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912154028867584
author Benko, Matej
Chlebicka, Iwona
Endal, Jørgen
Miasojedow, Błażej
author_facet Benko, Matej
Chlebicka, Iwona
Endal, Jørgen
Miasojedow, Błażej
contents We present a significant advancement in the field of Langevin Monte Carlo (LMC) methods by introducing the Inexact Proximal Langevin Algorithm (IPLA). This novel algorithm broadens the scope of problems that LMC can effectively address while maintaining controlled computational costs. IPLA extends LMC's applicability to potentials that are convex, strongly convex in the tails, and exhibit polynomial growth, beyond the conventional $L$-smoothness assumption. Moreover, we extend LMC's applicability to super-quadratic potentials and offer improved convergence rates over existing algorithms. Additionally, we provide bounds on all moments of the Markov chain generated by IPLA, enhancing its analytical robustness.
format Preprint
id arxiv_https___arxiv_org_abs_2412_09698
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Langevin Monte Carlo Beyond Lipschitz Gradient Continuity
Benko, Matej
Chlebicka, Iwona
Endal, Jørgen
Miasojedow, Błażej
Machine Learning
We present a significant advancement in the field of Langevin Monte Carlo (LMC) methods by introducing the Inexact Proximal Langevin Algorithm (IPLA). This novel algorithm broadens the scope of problems that LMC can effectively address while maintaining controlled computational costs. IPLA extends LMC's applicability to potentials that are convex, strongly convex in the tails, and exhibit polynomial growth, beyond the conventional $L$-smoothness assumption. Moreover, we extend LMC's applicability to super-quadratic potentials and offer improved convergence rates over existing algorithms. Additionally, we provide bounds on all moments of the Markov chain generated by IPLA, enhancing its analytical robustness.
title Langevin Monte Carlo Beyond Lipschitz Gradient Continuity
topic Machine Learning
url https://arxiv.org/abs/2412.09698