Isotropic SGD: a Practical Approach to Bayesian Posterior Sampling

Abstract

In this work we define a unified mathematical framework to deepen our understanding of the role of stochastic gradient (SG) noise on the behavior of Markov chain Monte Carlo sampling (SGMCMC) algorithms. Our formulation unlocks the design of a novel, practical approach to posterior sampling, which makes the SG noise isotropic using a fixed learning rate that we determine analytically, and that requires weaker assumptions than existing algorithms. In contrast, the common traits of existing \sgmcmc algorithms is to approximate the isotropy condition either by drowning the gradients in additive noise (annealing the learning rate) or by making restrictive assumptions on the \sg noise covariance and the geometry of the loss landscape. Extensive experimental validations indicate that our proposal is competitive with the state-of-the-art on \sgmcmc, while being much more practical to use.

References in corpus (6)

• A Complete Recipe for Stochastic Gradient MCMC
• Essentially No Barriers in Neural Network Energy Landscape
• Preconditioned Stochastic Gradient Langevin Dynamics for Deep Neural Networks
• The Anisotropic Noise in Stochastic Gradient Descent: Its Behavior of Escaping from Sharp Minima and Regularization Effects
• Bridging the Gap between Stochastic Gradient MCMC and Stochastic Optimization
• On the Heavy-Tailed Theory of Stochastic Gradient Descent for Deep Neural Networks