Query lower bounds for log-concave sampling

MaRDI QIDQ6432223arXivFDO

Authors Sinho Chewi, Jaume de Dios Pont, Jerry Li, Chen Lu, Shyam Narayanan

Publication date 5 April 2023

Published in arXiv

arXiv classification

cs.DScs.LGmath.STstat.MLstat.TH

Abstract: Log-concave sampling has witnessed remarkable algorithmic advances in recent years, but the corresponding problem of proving lower bounds for this task has remained elusive, with lower bounds previously known only in dimension one. In this work, we establish the following query lower bounds: (1) sampling from strongly log-concave and log-smooth distributions in dimension $dge2$ requires $Omega(logkappa)$ queries, which is sharp in any constant dimension, and (2) sampling from Gaussians in dimension $d$ (hence also from general log-concave and log-smooth distributions in dimension $d$) requires $widetildeOmega(min(sqrtkappalogd,d))$ queries, which is nearly sharp for the class of Gaussians. Here $kappa$ denotes the condition number of the target distribution. Our proofs rely upon (1) a multiscale construction inspired by work on the Kakeya conjecture in harmonic analysis, and (2) a novel reduction that demonstrates that block Krylov algorithms are optimal for this problem, as well as connections to lower bound techniques based on Wishart matrices developed in the matrix-vector query literature.

Cited in

(1)

• Exact simulation of diffusions and improved algorithms for log-concave sampling

This page was built for publication: Query lower bounds for log-concave sampling

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6432223)