On Theorem 2.3 in "Prediction, Learning, and Games" by Cesa-Bianchi and Lugosi
Abstract
The note presents a modified proof of a loss bound for the exponentially weighted average forecaster with time-varying potential. The regret term of the algorithm is upper-bounded by sqrtn ln(N) (uniformly in n), where N is the number of experts and n is the number of steps.
0
Turn this paper into a lesson
ArcXiv compiles a structured reading guide from this paper's metadata: plain-English importance, contributions, prerequisite concepts, which sections to read first, flashcards, and a quiz. Grounded in the abstract, never invented.