Reproduce “Training Scale-Invariant Neural Networks on the Sphere Can Happen in Three Regimes” 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

Maxim Kodryan, Ekaterina Lobacheva, Maksim Nakhodnov, Dmitry Vetrov

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.