Measuring sample quality with diffusions
Jackson Gorham, A. Duncan, Sebastian J. Vollmer et al. · The Annals of Applied Probability · 2019
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 Itô diffusions and develop explicit multivariate Stein factor bounds for any target with a fast-coupling Itô 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.
Cited by 74 works. doi:10.1214/19-aap1467 Open-access PDF
Authors
References
- Bayesian Data Analysis
- Multiple View Geometry in Computer Vision
- Fokker-Planck Equation
- Markov Processes
- Stochastic Integration and Differential Equations
- Markov Processes
- Stochastic Differential Equations
- Functions of Bounded Variation and Free Discontinuity Problems
- Stochastic Stability of Differential Equations
- Markov Chain Monte Carlo Maximum Likelihood