Skip to yearly menu bar Skip to main content


Poster

Learning to Explore for Stochastic Gradient MCMC

SeungHyun Kim · Seohyeon Jung · SeongHyeon Kim · Juho Lee

Hall C 4-9 #1414
[ ] [ Paper PDF ]
[ Poster
Tue 23 Jul 4:30 a.m. PDT — 6 a.m. PDT

Abstract:

Bayesian Neural Networks(BNNs) with high-dimensional parameters pose a challenge for posterior inference due to the multi-modality of the posterior distributions. Stochastic Gradient Markov Chain Monte Carlo(SGMCMC) with cyclical learning rate scheduling is a promising solution, but it requires a large number of sampling steps to explore high-dimensional multi-modal posteriors, making it computationally expensive. In this paper, we propose a meta-learning strategy to build SGMCMC which can efficiently explore the multi-modal target distributions. Our algorithm allows the learned SGMCMC to quickly explore the high-density region of the posterior landscape. Also, we show that this exploration property is transferrable to various tasks, even for the ones unseen during a meta-training stage. Using popular image classification benchmarks and a variety of downstream tasks, we demonstrate that our method significantly improves the sampling efficiency, achieving better performance than vanilla SGMCMC without incurring significant computational overhead.

Chat is not available.