Researchers say they have exactly characterized all optimal subgradient methods
prof_grimmer · x · 2026-07-23
A short arXiv note claims a complete characterization of all optimal subgradient methods.
The authors say prior work had found many distinct optimal subgradient methods, and their result exactly describes the full set of such methods. They also highlight the proof idea: ruling out any method outside the characterization using complementary slackness of optimal methods themselves.
More from Research
- Orthologic type systems argue for union, intersection, negation — but not distributivity — burny_tech · 2026-07-23
- New pediatrics paper calls for data, governance, and trust infrastructure for AI — IAmSamFin · 2026-07-23
- Paper claims 0.77% training, but released checkpoint actually uses 6.31% of parameters — yoavartzi · 2026-07-23
- A proof workflow cycles through failure, adversarial audit, and repair — burny_tech · 2026-07-23
- Math researcher warns that AI-generated proofs should be understood, not reposted — littmath · 2026-07-23
- Robotics deployments are now about data versus territory, not just flashy demos — broodsugar · 2026-07-23