Saved in:
Bibliographic Details
Main Authors: Chen, Yifan, Cheng, Xiaoou, Niles-Weed, Jonathan, Weare, Jonathan
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2408.13115
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912569165348864
author Chen, Yifan
Cheng, Xiaoou
Niles-Weed, Jonathan
Weare, Jonathan
author_facet Chen, Yifan
Cheng, Xiaoou
Niles-Weed, Jonathan
Weare, Jonathan
contents The unadjusted Langevin algorithm is commonly used to sample probability distributions in extremely high-dimensional settings. However, existing analyses of the algorithm for strongly log-concave distributions suggest that, as the dimension $d$ of the problem increases, the number of iterations required to ensure convergence within a desired error in the $W_2$ metric scales in proportion to $d$ or $\sqrt{d}$. In this paper, we argue that, despite this poor scaling of the $W_2$ error for the full set of variables, the behavior for a small number of variables can be significantly better: a number of iterations proportional to $K$, up to logarithmic terms in $d$, often suffices for the algorithm to converge to within a desired $W_2$ error for all $K$-marginals. We refer to this effect as delocalization of bias. We show that the delocalization effect does not hold universally and prove its validity for Gaussian distributions and strongly log-concave distributions with certain sparse interactions. Our analysis relies on a novel $W_{2,\ell^\infty}$ metric to measure convergence. A key technical challenge we address is the lack of a one-step contraction property in this metric. Finally, we use asymptotic arguments to explore potential generalizations of the delocalization effect beyond the Gaussian and sparse interactions setting.
format Preprint
id arxiv_https___arxiv_org_abs_2408_13115
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Convergence of Unadjusted Langevin in High Dimensions: Delocalization of Bias
Chen, Yifan
Cheng, Xiaoou
Niles-Weed, Jonathan
Weare, Jonathan
Machine Learning
Probability
Computation
The unadjusted Langevin algorithm is commonly used to sample probability distributions in extremely high-dimensional settings. However, existing analyses of the algorithm for strongly log-concave distributions suggest that, as the dimension $d$ of the problem increases, the number of iterations required to ensure convergence within a desired error in the $W_2$ metric scales in proportion to $d$ or $\sqrt{d}$. In this paper, we argue that, despite this poor scaling of the $W_2$ error for the full set of variables, the behavior for a small number of variables can be significantly better: a number of iterations proportional to $K$, up to logarithmic terms in $d$, often suffices for the algorithm to converge to within a desired $W_2$ error for all $K$-marginals. We refer to this effect as delocalization of bias. We show that the delocalization effect does not hold universally and prove its validity for Gaussian distributions and strongly log-concave distributions with certain sparse interactions. Our analysis relies on a novel $W_{2,\ell^\infty}$ metric to measure convergence. A key technical challenge we address is the lack of a one-step contraction property in this metric. Finally, we use asymptotic arguments to explore potential generalizations of the delocalization effect beyond the Gaussian and sparse interactions setting.
title Convergence of Unadjusted Langevin in High Dimensions: Delocalization of Bias
topic Machine Learning
Probability
Computation
url https://arxiv.org/abs/2408.13115