Langevin Monte Carlo Beyond Lipschitz Gradient Continuity
Abstract
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.
Cite
Text
Benko et al. "Langevin Monte Carlo Beyond Lipschitz Gradient Continuity." AAAI Conference on Artificial Intelligence, 2025. doi:10.1609/AAAI.V39I15.33706Markdown
[Benko et al. "Langevin Monte Carlo Beyond Lipschitz Gradient Continuity." AAAI Conference on Artificial Intelligence, 2025.](https://mlanthology.org/aaai/2025/benko2025aaai-langevin/) doi:10.1609/AAAI.V39I15.33706BibTeX
@inproceedings{benko2025aaai-langevin,
title = {{Langevin Monte Carlo Beyond Lipschitz Gradient Continuity}},
author = {Benko, Matej and Chlebicka, Iwona and Endal, Jørgen and Miasojedow, Blazej},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2025},
pages = {15541-15549},
doi = {10.1609/AAAI.V39I15.33706},
url = {https://mlanthology.org/aaai/2025/benko2025aaai-langevin/}
}