Reproduce “Provable Stochastic Optimization for Global Contrastive Learning: Small Batch Does Not Harm Performance” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Zhuoning Yuan, Yuexin Wu, Zi-Hao Qiu, Xianzhi Du, Lijun Zhang, Denny Zhou, Tianbao Yang
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.