Skip to yearly menu bar Skip to main content


Poster

Constrained Exploration via Reflected Replica Exchange Stochastic Gradient Langevin Dynamics

Haoyang Zheng · Hengrong Du · Qi Feng · Wei Deng · Guang Lin

Hall C 4-9 #1608
[ ] [ Paper PDF ]
[ Poster
Tue 23 Jul 2:30 a.m. PDT — 4 a.m. PDT

Abstract:

Replica exchange stochastic gradient Langevin dynamics (reSGLD) is an effective sampler for non-convex learning in large-scale datasets. However, the simulation may encounter stagnation issues when the high-temperature chain delves too deeply into the distribution tails. To tackle this issue, we propose reflected reSGLD (r2SGLD): an algorithm tailored for constrained non-convex exploration by utilizing reflection steps within a bounded domain. Theoretically, we observe that reducing the diameter of the domain enhances mixing rates, exhibiting a quadratic behavior. Empirically, we test its performance through extensive experiments, including identifying dynamical systems with physical constraints, simulations of constrained multi-modal distributions, and image classification tasks. The theoretical and empirical findings highlight the crucial role of constrained exploration in improving the simulation efficiency.

Chat is not available.