An Improved Analysis of Langevin Algorithms with Prior Diffusion for Non-Log-Concave Sampling
arxiv(2024)
摘要
Understanding the dimension dependency of computational complexity in
high-dimensional sampling problem is a fundamental problem, both from a
practical and theoretical perspective. Compared with samplers with unbiased
stationary distribution, e.g., Metropolis-adjusted Langevin algorithm (MALA),
biased samplers, e.g., Underdamped Langevin Dynamics (ULD), perform better in
low-accuracy cases just because a lower dimension dependency in their
complexities. Along this line, Freund et al. (2022) suggest that the modified
Langevin algorithm with prior diffusion is able to converge dimension
independently for strongly log-concave target distributions. Nonetheless, it
remains open whether such property establishes for more general cases. In this
paper, we investigate the prior diffusion technique for the target
distributions satisfying log-Sobolev inequality (LSI), which covers a much
broader class of distributions compared to the strongly log-concave ones. In
particular, we prove that the modified Langevin algorithm can also obtain the
dimension-independent convergence of KL divergence with different step size
schedules. The core of our proof technique is a novel construction of an
interpolating SDE, which significantly helps to conduct a more accurate
characterization of the discrete updates of the overdamped Langevin dynamics.
Our theoretical analysis demonstrates the benefits of prior diffusion for a
broader class of target distributions and provides new insights into developing
faster sampling algorithms.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要