Stochastic Proximal Langevin Algorithm: Potential Splitting and Nonasymptotic Rates
arXiv:1905.11768
Abstract
We propose a new algorithm---Stochastic Proximal Langevin Algorithm (SPLA)---for sampling from a log concave distribution. Our method is a generalization of the Langevin algorithm to potentials expressed as the sum of one stochastic smooth term and multiple stochastic nonsmooth terms. In each iteration, our splitting technique only requires access to a stochastic gradient of the smooth term and a stochastic proximal operator for each of the nonsmooth terms. We establish nonasymptotic sublinear and linear convergence rates under convexity and strong convexity of the smooth term, respectively, expressed in terms of the KL divergence and Wasserstein distance. We illustrate the efficiency of our sampling technique through numerical simulations on a Bayesian learning task.
References in corpus (11)
- Rényi Divergence and Kullback-Leibler Divergence
- User-friendly guarantees for the Langevin Monte Carlo with inaccurate gradient
- Underdamped Langevin MCMC: A non-asymptotic analysis
- Non-asymptotic convergence analysis for the Unadjusted Langevin Algorithm
- Is There an Analog of Nesterov Acceleration for MCMC?
- On the Theory of Variance Reduction for Stochastic Gradient Monte Carlo
- Sampling as optimization in the space of measures: The Langevin dynamics as a composite optimization problem
- Langevin Monte Carlo and JKO splitting
- Fractional Langevin Monte Carlo: Exploring Lévy Driven Stochastic Differential Equations for Markov Chain Monte Carlo
- Stochastic Three-Composite Convex Minimization
- Stochastic inertial primal-dual algorithms