Fig.1

Concept

Regret bound

A regret bound is a worst-case guarantee from online learning that limits how much worse your algorithm does than the single best fixed decision chosen in hindsight. Formally, regret after T steps is the sum of your per-step losses minus the sum of losses that a fixed…

The rest of “Regret bound” is a premium feature: every concept in the library gets a precise, practitioner-focused write-up like this one, cross-linked straight from the paper summaries that use it.

Log in to unlock

← Back to the library