Adaptive Hedging under Delayed Feedback

Abstract

The article is devoted to investigating the application of hedging strategies to online expert weight allocation under delayed feedback. As the main result we develop the General Hedging algorithm based on the exponential reweighing of experts’ losses. We build the artificial probabilistic framework and use it to prove the adversarial loss bounds for the algorithm in the delayed feedback setting. The designed algorithm can be applied to both countable and continuous sets of experts. We also show how algorithm extends classical Hedge (Multiplicative Weights) and adaptive Fixed Share algorithms to the delayed feedback and derive their regret bounds for the delayed setting by using our main result.

Alexander Korotin

Assistant professor,
research scientist

My research interests include generative modeling, unpaired learning, optimal transport and Schrodinger bridges.