Skip to content
conftrace_
2024 ICML ICML 2024

EMC$^2$: Efficient MCMC Negative Sampling for Contrastive Learning with Global Convergence

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

Authors

Chung-Yiu Yau, Hoi To Wai, Parameswaran Raman, Soumajyoti Sarkar, Mingyi Hong

Topics

Machine Learning > Learning Types > Contrastive Learning Machine Learning > Optimization & Theory > Bayesian Inference Deep Learning > Learning Types > Contrastive Learning

Keywords

stationary point batch size negative sampling softmax distribution global contrastive loss metropolis-hastings
Download PDF