Projected Stochastic Gradient Langevin Algorithms for Constrained Sampling and Non-Convex Learning

Abstract

Langevin algorithms are gradient descent methods with additive noise. They have been used for decades in Markov chain Monte Carlo (MCMC) sampling, optimization, and learning. Their convergence properties for unconstrained non-convex optimization and learning problems have been studied widely in the last few years. Other work has examined projected Langevin algorithms for sampling from log-concave distributions restricted to convex compact sets. For learning and optimization, log-concave distributions correspond to convex losses. In this paper, we analyze the case of non-convex losses with compact convex constraint sets and IID external data variables. We term the resulting method the projected stochastic gradient Langevin algorithm (PSGLA). We show the algorithm achieves a deviation of $O(T^{-1/4}(\log T{)}^{1/2})$ from its target distribution in 1-Wasserstein distance. For optimization and learning, we show that the algorithm achieves $\epsilon$-suboptimal solutions, on average, provided that it is run for a time that is polynomial in ${\epsilon }^{-1}$ and slightly super-exponential in the problem dimension.

arXiv comment45 pages. Under Review for COLT 2021

References in corpus (6)

• Non-convex learning via Stochastic Gradient Langevin Dynamics: a nonasymptotic analysis
• On stochastic gradient Langevin dynamics with dependent data streams: the fully non-convex case
• Sampling from a log-concave distribution with compact support with proximal Langevin Monte Carlo
• Wasserstein Control of Mirror Langevin Monte Carlo
• Efficient constrained sampling via the mirror-Langevin algorithm
• Acceleration and Averaging in Stochastic Mirror Descent Dynamics