Skip to content
Preprint

High-accuracy simulation of Picard HMC, part I: Gaussian cloud correction

Sep 2026 · 1 citation · ⚡ 1 influential
Mathematics Computer Science

TL;DR

The Gaussian cloud sampler is introduced and the algorithm uses first-order rejection sampling (FORS) to correct the law of smoothed Picard HMC trajectories and a suite of likelihood correction gadgets which only use samples from this indirect cloud representation are developed.

Abstract

We study the problem of sampling from a continuous density $\pi\propto \exp(-V)$ on $\mathbb R^d$, where $V\in C^2(\mathbb R^d)$ has a $\beta$-Lipschitz gradient and $\pi$ satisfies a logarithmic Sobolev inequality with constant $\alpha^{-1}$, and write $\kappa = \beta/\alpha$. We introduce the Gaussian cloud sampler, which achieves total variation accuracy $\varepsilon$ using $\widetilde O(\kappa d^{1/5}\,\text{polylog}(1/\varepsilon))$ gradient queries in expectation. The algorithm uses first-order rejection sampling (FORS) to correct the law of smoothed Picard HMC trajectories. To do so, we represent the iterates of the ideal Picard iteration via Gaussian clouds, whose centers are never evaluated, and we develop a suite of likelihood correction gadgets which only use samples from this indirect cloud representation.

View source

Similar papers

#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

A stochastic subgradient method with optimal failure exponent

Fix a target accuracy $\varepsilon$, a gradient-noise level $s$, and a horizon $N$. We wish to design algorithms which minimize the probability of observing a suboptimality gap which exceeds the target accuracy, i.e., $\mathcal{E}_N = -\log \sup_{f,P} \mathbb{P}_P(f(x_A) - f_\star \ge \varepsilon)$, with the noise law...

B. V. Van Parys · 0 citations
Preprint Nov 2026

Stochastic Homogenization of Schr\"odinger Equations with Exponentially Mixing Sub-Gaussian Potentials

We study the stochastic Schr\"odinger equation $ i\partial_t u_{\varepsilon} = H_{\varepsilon} u_{\varepsilon} $ with $ H_{\varepsilon} = -\Delta + V(x/\varepsilon) $, where V is a stationary ergodic sub-Gaussian field with exponential mixing. We establish the optimal algebraic error rate $ \varepsilon^{d/2} $ in $ L^2...

Fan-Fei Meng · 0 citations
Preprint Nov 2026

Subpolynomial-Query Proximal Sampling Beyond Log-Concavity

This work implements its observation chain using the high-order noisy conditional sampler of [OpenAI 2026], obtaining improved dimension dependence under functional inequalities and obtaining a corresponding guarantee from a warm start with a known bound on its R\'enyi divergence.

Wei Guo, Bo Yuan, Ye He et al. · 0 citations
Preprint Oct 2026

A New Bound for the Gauss Circle Problem

Let $E(X)=\#\{(a,b)\in\Z^2:a^2+b^2\le X\}-\pi X$. We prove that $E(X)=O_\varepsilon(X^{209/670+\varepsilon})$ for every $\varepsilon>0$, uniformly for real $X\ge4$. This breaks the $5/16$ threshold suggested by Huxley as a possible limit of the Bombieri--Iwaniec method at the time. The proof introduces two refinements:...

Xi Cen, Xi-Tao Gao, Cheng Zhang et al. · 0 citations
Preprint Oct 2026

Polytope Sampling at the Speed of Isoperimetry

We give faster algorithms for sampling from the uniform distribution over a polytope. Our main result is an algorithm that, when applied to a polytope with $m$ constraints in $n$ dimensions, uses $m \cdot \mathrm{poly}\log(\frac m \delta)$ iterations, each running in time $O(mn^{\omega - 1})$, to return a sample within...

An-Ming Gu, Bobby Shi, K. Tian et al. · 0 citations

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