Reproduce “Subsampling is not Magic: Why Large Batch Sizes Work for Differentially Private Stochastic Optimisation” 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
Ossi Räisä, Joonas Jälkö, Antti Honkela
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.