27-Year-Old Open Problem Closed: Sharp SVM Margin-Based Generalization Bound Proven
LucaAmb · x · 2026-09-16
Researchers @aryehazan and Steve Hanneke, with the help of an AI assistant, announce they have resolved the sharp realizable margin-based generalization bound for SVMs, an open problem since the 1998 Shawe-Taylor/Bartlett/Williamson/Anthony bound that carried extra log factors.
- The authors had a false start in their 2020 ALT paper, which this result makes up for
- Paper link shared in the follow-up comment
More from Research
- Radial gate objective cuts diffusion transformer FID from 16.24 to 11.83 — Junha Park · 2026-11-02
- REA: async brain-cerebellum runtime for robots where policies never wait on the LLM — Pengfei Zhou · 2026-11-02
- Microsoft's MemSteer turns unlabeled user histories into agent memory supervision — MicrosoftResearch · 2026-11-02
- SciGame benchmark uses counterfactual worlds to expose LLM agents' priors vs evidence — Yusheng Zhao · 2026-11-02
- On Terence Tao's blog, Frank Calegari calls on mathematicians to adapt after OpenAI's 700-paper release — Hesamation · 2026-11-02
- Tsinghua & Microsoft's HarnessMM cuts agent token use by up to 87.93% while raising success rate — rohanpaul_ai · 2026-11-02