2 papers
math.OC2026
Insights on Muon from Simple Quadratics
Antoine Gonon, Andreea-Alexandra MuÅat, Nicolas Boumal
Muon updates weight matrices along (approximate) polar factors of the gradients and has shown strong empirical performance in large-scale training. Existing attempts at explaining…
cs.LG2026
Gaussian Match-and-Copy: A Minimalist Benchmark for Studying Transformer Induction
Antoine Gonon, Alexandre Cordonnier, Nicolas Boumal
Match-and-copy is a core retrieval primitive used at inference time by large language models to retrieve a matching token from the context then copy its successor. Yet, understandi…