Reproduce “Gradient Descent can Learn Less Over-parameterized Two-layer Neural Networks on Classification Problems” 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
Atsushi Nitanda, Geoffrey Chinot, Taiji Suzuki
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.