SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2408.09140 · 2024

Learning to Explore for Stochastic Gradient MCMC

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

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 MCMC(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 \gls{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 \gls{sgmcmc} without incurring significant computational overhead.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2408.09140")
get_code_for_paper("2408.09140")
have("2408.09140")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2408.09140.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2408.09140.svg)](https://syntology.ai/paper/2408.09140)

Connect an agent — have() is free.