Provable Stochastic Optimization for Global Contrastive Learning: Small Batch Does Not Harm Performance

Zhuoning Yuan, Yuexin Wu, Zi-Hao Qiu, Xianzhi Du, Lijun Zhang, Denny Zhou, Tianbao Yang. Provable Stochastic Optimization for Global Contrastive Learning: Small Batch Does Not Harm Performance. In Kamalika Chaudhuri, Stefanie Jegelka, Le Song, Csaba Szepesvári, Gang Niu 0001, Sivan Sabato, editors, International Conference on Machine Learning, ICML 2022, 17-23 July 2022, Baltimore, Maryland, USA. Volume 162 of Proceedings of Machine Learning Research, pages 25760-25782, PMLR, 2022. [doi]

Abstract

Abstract is missing.