Online boosting algorithm: weak learning assumption and gradient boosting guarantee
Aaroth · x · 2026-08-14
Aaroth explains that the weak learning assumption is that no such distribution exists, so if it holds, error is low. Adding an orthogonality condition allows competing with any predictor in the span of the weak class, the usual gradient boosting guarantee.
More from Research
- First Agent Memory Leaderboard launches; MemoraX tops commercial text-memory track — rohanpaul_ai · 2026-08-14
- Anthropic Frontier Red Team Report: Multi-Agent Systems Face Cooperation and Trust Issues — dhadfieldmenell · 2026-08-14
- Microsoft folds Normuon row-norm into row selection for modest gains — JohnCLangford · 2026-08-14
- Scale learning rate by 1/sqrt(f) when sampling rows, Microsoft finds — JohnCLangford · 2026-08-14
- Microsoft Open-Sources Dion Optimizer: Integrates Gram-NS, Row Selection, and More, 6x Faster Training — JohnCLangford · 2026-08-14
- Claude Teaches Gemma Tetris: Score Rises 0 to 16 in 2.5 Days, Exposes Agent Infrastructure Flaws — TheZachMueller · 2026-08-14