Stochastic Gradient and Langevin Processes

Xiang Cheng · Dong Yin · Peter Bartlett · Michael Jordan

Keywords: [ Gaussian Processes ] [ Monte Carlo Methods ] [ Optimization ] [ Probabilistic Inference - Approximate, Monte Carlo, and Spectral Methods ]

[ Abstract ] [ Join Zoom
Please do not share or post zoom links


We prove quantitative convergence rates at which discrete Langevin-like processes converge to the invariant distribution of a related stochastic differential equation. We study the setup where the additive noise can be non-Gaussian and state-dependent and the potential function can be non-convex. We show that the key properties of these processes depend on the potential function and the second moment of the additive noise. We apply our theoretical findings to studying the convergence of Stochastic Gradient Descent (SGD) for non-convex problems and corroborate them with experiments using SGD to train deep neural networks on the CIFAR-10 dataset.

Chat is not available.