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

Abstract

Let $π(\mathrm{d} x)\propto e^{-U(x)}\,\mathrm{d} x$ 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 $κ=L/m$. It is known that, under warm-start assumptions, fixed-step Metropolis-adjusted Langevin algorithm (MALA) with properly tuned step size has mixing time of order $κ\sqrt{d}$ up to logarithmic factors. By contrast, when the condition number is bounded away from one, no single fixed step size yields a matching spectral-gap lower bound of order $(κ\sqrt{d})^{-1}$ uniformly over this target class. We establish a global spectral-gap lower bound for MALA with a uniformly randomized step size. At each iteration, the algorithm draws $h$ uniformly from $(0,H)$ and performs one ordinary MALA transition. Choosing $H$ of order $$\frac{1}{L\sqrt{d[1+\log(d+1)+\logκ]}}$$ yields a right spectral-gap lower bound of order $$\frac{1}{κ\sqrt{d[1+\log(d+1)+\logκ]}},$$ uniformly over the target class. A key ingredient in the proof is a Cheeger-type inequality for aggregating estimates of the one-step flow of MALA out of measurable sets at various step-size scales. It allows the scale used to control the flow to depend on the set and avoids the additional loss that would result from first estimating the conductance and then applying the standard Cheeger inequality. This work was developed with substantial assistance from ChatGPT, which suggested the uniformly randomized-step approach, developed the principal proof arguments, and generated the simulation and Lean 4 code. The human author checked and verified the mathematical content and takes full responsibility for the results.