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.
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· arXiv.org· 0 citations
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...
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...
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...
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
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...