LLM-Assisted Proof Shows GD's Silver Rate Is Optimal, Latest Math Breakthrough
burny_tech · x · 2026-10-08
Researcher YyuhanYe reports proving a lower bound of n^{-(p+C√(log log n / log n))} with p=log₂(1+√2) for gradient descent with predetermined nonnegative stepsizes in smooth convex optimization — after extensive interaction with ChatGPT 6 — showing the silver exponent is optimal. The reposter adds context that LLMs recently also resolved the latest theoretical bound for matmul, marking a notable milestone for LLMs contributing to theoretical math.
More from Research
- Kernaut: coding agents design Gaussian process kernels via program search — sirbayes · 2026-10-08
- iOSWorld brings computer-use agent benchmarking to iOS at COLM 2026 — kohjingyu · 2026-10-08
- Epoch's InnovationEval: AI agents still far from producing real research innovations — Afinetheorem · 2026-10-08
- Dankrad: AI's inelegant math results reveal human bias from small context windows — CatAstro_Piyush · 2026-10-08
- Lilly and Novo trial data show GLP-1s reduce biological age, reports MIT Tech Review — MaxUnfried · 2026-10-08
- 113 decision models in 3 weeks: 70 built on Qwen, sub-cent per call — jonathanmalkin · 2026-10-08