Online boosting algorithm achieves adaptive guarantees on sub-intervals via hard core distribution

Aaroth · x · 2026-08-14

Aaroth explains that standard online learning tricks make the boosting guarantee adaptive, holding on every sub-interval where the weak learning condition is satisfied, even if not on others. This works through an adaptive version of a hard core distribution.

Related event: Online Boosting Offers Adaptive Guarantees on Subintervals(2 posts)→

Original post →

More from Research

Research channel →