Sampling with Mirrored Stein Operators

Abstract

We introduce a new family of particle evolution samplers suitable for constrained domains and non-Euclidean geometries. Stein Variational Mirror Descent and Mirrored Stein Variational Gradient Descent minimize the Kullback-Leibler (KL) divergence to constrained target distributions by evolving particles in a dual space defined by a mirror map. Stein Variational Natural Gradient exploits non-Euclidean geometry to more efficiently minimize the KL divergence to unconstrained targets. We derive these samplers from a new class of mirrored Stein operators and adaptive kernels developed in this work. We demonstrate that these new samplers yield accurate approximations to distributions on the simplex, deliver valid confidence intervals in post-selection inference, and converge more rapidly than prior methods in large-scale unconstrained posterior inference. Finally, we establish the convergence of our new procedures under verifiable conditions on the target distribution.

ICLR 2022; Source code: https://github.com/thjashin/mirror-stein-samplers

References in corpus (24)

• Reinforcement Learning with Deep Energy-Based Policies
• New insights and perspectives on the natural gradient method
• Preconditioned Stochastic Gradient Langevin Dynamics for Deep Neural Networks
• Stein Variational Gradient Descent as Gradient Flow
• Measuring Sample Quality with Stein's Method
• Langevin diffusions and the Metropolis-adjusted Langevin algorithm
• A Kernel Test of Goodness of Fit
• Measuring Sample Quality with Kernels
• Large sample analysis of the median heuristic
• Message Passing Stein Variational Gradient Descent
• A Spectral Approach to Gradient Estimation for Implicit Distributions
• A Linear-Time Kernel Goodness-of-Fit Test
• Stein Variational Gradient Descent With Matrix-Valued Kernels
• A Stein variational Newton method
• Is There an Analog of Nesterov Acceleration for MCMC?
• Projected Stein Variational Newton: A Fast and Scalable Bayesian Inference Method in High Dimensions
• A Non-Asymptotic Analysis for Stein Variational Gradient Descent
• Random Feature Stein Discrepancies
• Stein Point Markov Chain Monte Carlo
• Exponential ergodicity of mirror-Langevin diffusions
• Wasserstein Control of Mirror Langevin Monte Carlo
• Stochastic Stein Discrepancies
• Efficient constrained sampling via the mirror-Langevin algorithm
• Non-reversible, tuning- and rejection-free Markov chain Monte Carlo via iterated random functions