Detail publikace
Langevin Monte Carlo Beyond Lipschitz Gradient Continuity
BENKO, M. CHLEBICKA, I. MIASOJEDOW, B. ENDAL, J.
Originální název
Langevin Monte Carlo Beyond Lipschitz Gradient Continuity
Typ
článek ve sborníku ve WoS nebo Scopus
Jazyk
angličtina
Originální abstrakt
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.
Klíčová slova
Computational costs; Convergence rates; Improved convergence; Langevin algorithms; Langevin Monte-Carlo; Lipschitz gradients; MonteCarlo methods; Novel algorithm; Polynomial growths
Autoři
BENKO, M.; CHLEBICKA, I.; MIASOJEDOW, B.; ENDAL, J.
Vydáno
11. 4. 2025
Nakladatel
Association for the Advancement of Artificial Intelligence
Místo
Philadelphia
ISBN
978-1-57735-897-8
Kniha
Proceedings of the 39th Annual AAAI Conference on Artificial Intelligence
Strany od
15541
Strany do
15549
Strany počet
9
URL
BibTex
@inproceedings{BUT198313,
author="Matej {Benko} and Iwona {Chlebicka} and Endal {Jørgen} and Błażej {Miasojedow}",
title="Langevin Monte Carlo Beyond Lipschitz Gradient Continuity",
booktitle="Proceedings of the 39th Annual AAAI Conference on Artificial Intelligence",
year="2025",
pages="15541--15549",
publisher="Association for the Advancement of Artificial Intelligence",
address="Philadelphia",
doi="10.1609/aaai.v39i15.33706",
isbn="978-1-57735-897-8",
url="https://ojs.aaai.org/index.php/AAAI/article/view/33706"
}
Odpovědnost: Ing. Marek Strakoš