Bridging Mini-Batch and Asymptotic Analysis in Contrastive Learning: From InfoNCE to Kernel-Based Losses

Panagiotis Koromilas; Giorgos Bouritsas; Theodoros Giannakopoulos; Mihalis Nicolaou; Yannis Panagakis

2024 ICML ICML 2024

Bridging Mini-Batch and Asymptotic Analysis in Contrastive Learning: From InfoNCE to Kernel-Based Losses

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

Panagiotis Koromilas, Giorgos Bouritsas, Theodoros Giannakopoulos, Mihalis Nicolaou, Yannis Panagakis

Topics

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

Keywords

contrastive learning info nce batch size independence dhel hyperspherical energy minimisation kernel-based losses

Download PDF