On stochastic gradient Langevin dynamics with dependent data streams in the logconcave case

Abstract

We study the problem of sampling from a probability distribution $\pi$ on $\rset^d$ which has a density \wrt\ the Lebesgue measure known up to a normalization factor $x \mapsto \rme^{-U(x)} / \int_{\rset^d} \rme^{-U(y)} \rmd y$. We analyze a sampling method based on the Euler discretization of the Langevin stochastic differential equations under the assumptions that the potential $U$ is continuously differentiable, $\nabla U$ is Lipschitz, and $U$ is strongly concave. We focus on the case where the gradient of the log-density cannot be directly computed but unbiased estimates of the gradient from possibly dependent observations are available. This setting can be seen as a combination of a stochastic approximation (here stochastic gradient) type algorithms with discretized Langevin dynamics. We obtain an upper bound of the Wasserstein-2 distance between the law of the iterates of this algorithm and the target distribution $\pi$ with constants depending explicitly on the Lipschitz and strong convexity constants of the potential and the dimension of the space. Finally, under weaker assumptions on $U$ and its gradient but in the presence of independent observations, we obtain analogous results in Wasserstein-2 distance.

arXiv comment35 pages

References in corpus (6)

• User-friendly guarantees for the Langevin Monte Carlo with inaccurate gradient
• Non-convex learning via Stochastic Gradient Langevin Dynamics: a nonasymptotic analysis
• Non-asymptotic convergence analysis for the Unadjusted Langevin Algorithm
• On the Theory of Variance Reduction for Stochastic Gradient Monte Carlo
• On stochastic gradient Langevin dynamics with dependent data streams: the fully non-convex case
• Global Convergence of Langevin Dynamics Based Algorithms for Nonconvex Optimization

Cited by in corpus (4)

• Nonasymptotic estimates for Stochastic Gradient Langevin Dynamics under local conditions in nonconvex optimization
• A fully data-driven approach to minimizing CVaR for portfolio of assets via SGLD with discontinuous updating
• Structured Logconcave Sampling with a Restricted Gaussian Oracle
• Convergence Analysis of Schr{ö}dinger-F{ö}llmer Sampler without Convexity