Skip to content
Preprint

A spectral gap for Metropolis-adjusted Langevin algorithm with a uniformly randomized step size

Sep 2026 · 0 citations
Mathematics

Abstract

Let $\pi(\mathrm{d} x)\propto e^{-U(x)}\, \mathrm{d} x$ on $\mathbb{R}^d$, where $U$ is continuously differentiable and $m$-strongly convex with a globally $L$-Lipschitz gradient, $0<m\leq L<\infty$, and $\kappa=L/m$. Fixed-step Metropolis-adjusted Langevin algorithm (MALA) has known warm-start mixing-time upper bounds of order $\kappa\sqrt d$, up to logarithmic factors. A spectral-gap lower bound at the corresponding scale $(\kappa \sqrt{d})^{-1}$ would give an upper bound of order $\kappa \sqrt{d}$ on the Monte Carlo asymptotic variance relative to independent sampling, uniformly over all square-integrable functions. However, when $\kappa$ is bounded away from~1, the best fixed-step spectral gap that can be guaranteed uniformly over this target class is at most of order $\max\{\log(\kappa d)/(\kappa d), e^{-cd}\}$ for some positive universal constant~$c$. We show that uniform randomization of the step size improves this worst-case guarantee. At each iteration, the algorithm draws $h\sim\operatorname{Unif}(0,H)$ and performs one ordinary MALA transition. Choosing $H$ of order $[L\sqrt{d(1+\log d+\log\kappa)}]^{-1}$ yields a right spectral-gap lower bound of order \[ \frac{1}{\kappa\sqrt{d(1+\log d+\log\kappa)}}, \] uniformly over the target class. Thus, given $\kappa>1$, for all square-integrable functions, the ratio of the Monte Carlo asymptotic variance relative to independence sampling has an upper bound of order $\sqrt{d \log d}$. This contrasts with fixed-MALA, where the ratio can be as bad as $d/\log d$ in thew worst-case scenario. The spectral gap also gives geometric convergence of the lazy kernel from every initial density in $L^2(\pi)$, central limit theorems, and nonstationary mean-square error bounds. This work was developed with substantial assistance from ChatGPT.

View source

Similar papers

Sep 2026

Geometric mean quantization via adaptive approximation

Let $\nu$ be a compactly supported Borel probability measure on $\mathbb R^{d}$ with $\nu(B(x,r))\leq Cr^{a}$ for some $a>0$. Refine a dyadic cube exactly when its mass is at least $t$, and let $\mathcal{L}_{\nu}(t)$ be the mean depth at which this refinement stops. We show that the lower and upper geometric-mean quant...

M. Kessebohmer, Aljoscha Niemann · 0 citations
#machine learning Preprint Oct 2026

Optimal Oracle Complexity for Finite-Sum Monotone Inclusions

We present an oracle-optimal method for finite-sum monotone inclusions under mean-square Lipschitz continuity. Our switching regularization method finds a point $y$ and a certificate $g\in G(y)$ with $(\mathbb{E}\|F(y)+g\|^2)^{1/2}\le\varepsilon$ using $\mathcal{O}(n+\sqrt{n}LR/\varepsilon)$ expected component evaluati...

Qi-Hao Zhou · 1 citation
#machine learning Preprint Sep 2026

Poisson-Corrector Complexity Bounds for Moreau--Yosida Unadjusted Langevin Sampling

We study the classical Moreau--Yosida unadjusted Langevin algorithm (MYULA) for $\pi(\,\mathrm{d} x)\propto e^{-f(x)-g(x)}\,\mathrm{d} x$, where $f\in C^2(\mathbb{R}^d)$ is $m$-strongly convex with $L_f$-Lipschitz gradient and $g:\mathbb{R}^d\to\mathbb{R}$ is convex and globally $G$-Lipschitz. For the Moreau-smoothed t...

Yu-Chen Xin, Zhi-Hua Zhang · 0 citations
Preprint Sep 2026

Dimension-free estimates for the full discrete Euclidean ball maximal function

Let $M_t$ denote the normalized average over the lattice points in the Euclidean ball of radius $t$ in $\mathbb{Z}^d$. We prove that the full maximal operator $f\mapsto\sup_{t\geq0}\lvert M_t f\rvert$ is bounded on $\ell^p(\mathbb{Z}^d)$, for every $1<p\leq\infty$, with a constant independent of the dimension. In parti...

Sheng-Chen Mao · 0 citations
#machine learning Preprint Oct 2026

Sharp dimensional analysis of midpoint methods for Langevin sampling

The proofs exploit cancellation at stationarity and smoothing using techniques from Malliavin calculus, outperforming previous upper bounds based on standard couplings and shows surprisingly that in high dimensions, deterministic discretizations can outperform their random counterparts.

Fan Chen, Sinho Chewi, Jian-Feng Lu et al. · 0 citations
Preprint Sep 2026

Joint Lower Bounds for Zeroth-Order Nonconvex Optimization on Euclidean Balls

We prove a joint stochastic zeroth-order lower bound for Goldstein stationarity on a Euclidean query ball, even when the ball is guaranteed to contain a stationary point. In dimension $d$, let $f=\mathbb{E}[F(\cdot;\xi)]$, assume $\mathbb{E}[\operatorname{Lip}(F(\cdot;\xi))^2]\le L_0^2$, and bound the initial objective...

Hai-Han Zhang, Wen-Dao Wu, Chen-Heng Zhang et al. · 3 citations · ⚡1

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.