1 code implementation • NeurIPS 2021 • Jeffrey Negrea, Blair Bilodeau, Nicolò Campolongo, Francesco Orabona, Daniel M. Roy
Quantile (and, more generally, KL) regret bounds, such as those achieved by NormalHedge (Chaudhuri, Freund, and Hsu 2009) and its variants, relax the goal of competing against the best individual expert to only competing against a majority of experts on adversarial data.
no code implementations • 15 Feb 2021 • Nicolò Campolongo, Francesco Orabona
Our proposed algorithm is adaptive not only to the temporal variability of the loss functions, but also to the path length of the sequence of comparators when an upper bound is known.
no code implementations • NeurIPS 2020 • Nicolò Campolongo, Francesco Orabona
We prove a novel static regret bound that depends on the temporal variability of the sequence of loss functions, a quantity which is often encountered when considering dynamic competitors.