paper-with-me

홈 › Papers

Measuring Sample Quality with Diffusions

2016-11-21 · Jackson Gorham, Andrew B. Duncan, Sebastian J. Vollmer, Lester Mackey

Stein's method for measuring convergence to a continuous target distribution relies on an operator characterizing the target and Stein factor bounds on the solutions of an associated differential equation. While such operators and bounds are readily available for a diversity of univariate targets, few multivariate targets have been analyzed. We introduce a new class of characterizing operators based on Ito diffusions and develop explicit multivariate Stein factor bounds for any target with a fast-coupling Ito diffusion. As example applications, we develop computable and convergence-determining diffusion Stein discrepancies for log-concave, heavy-tailed, and multimodal targets and use these quality measures to select the hyperparameters of biased Markov chain Monte Carlo (MCMC) samplers, compare random and deterministic quadrature rules, and quantify bias-variance tradeoffs in approximate MCMC. Our results establish a near-linear relationship between diffusion Stein discrepancies and Wasserstein distances, improving upon past work even for strongly log-concave targets. The exposed relationship between Stein factors and Markov process coupling may be of independent interest.

📄 PDF Abstract BibTeX arXiv:1611.06972

Code (0)

등록된 구현이 없습니다.

Tasks

Diversity

Similar Papers 제목 키워드 기반

Where to Diffuse, How to Diffuse, and How to Get Back: Automated Learning for Multivariate Diffusions

2023-02-14 · Raghav Singhal, Mark Goldstein, Rajesh Ranganath

Diffusion-based generative models (DBGMs) perturb data to a target noise distribution and reverse this process to generate samples. The choice of noising process, or inference diffusion process, affects both likelihoods …

Adaptive Path Integral Diffusion: AdaPID

2025-12-05 · Michael Chertkov, Hamidreza Behjoo arxiv

Diffusion-based samplers -- Score Based Diffusions, Bridge Diffusions and Path Integral Diffusions -- match a target at terminal time, but the real leverage comes from choosing the schedule that governs the intermediate-…

Sampling, Diffusions, and Stochastic Localization

2023-05-18 · Andrea Montanari

Diffusions are a successful technique to sample from high-dimensional distributions can be either explicitly given or learnt from a collection of samples. They implement a diffusion process whose endpoint is a sample fro…

Denoising

Self-Speculative Masked Diffusions

2025-10-04 · Andrew Campbell, Valentin De Bortoli, Jiaxin Shi, Arnaud Doucet arxiv

We present self-speculative masked diffusions, a new class of masked diffusion generative models for discrete data that require significantly fewer function evaluations to generate samples. Standard masked diffusion mode…

A Unifying and Canonical Description of Measure-Preserving Diffusions

2021-05-06 · Alessandro Barp, So Takao, Michael Betancourt, Alexis Arnaudon 외

A complete recipe of measure-preserving diffusions in Euclidean space was recently derived unifying several MCMC algorithms into a single framework. In this paper, we develop a geometric theory that improves and generali…