Adaptive hedging under delayed feedback

Alexander Korotin, Vladimir V'yugin, Evgeny Burnaev

    Research output: Contribution to journalArticlepeer-review

    1 Citation (Scopus)

    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 G 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 G in the delayed feedback setting. The designed algorithm G can be applied to both countable and continuous sets of experts. We also show how algorithm G 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.

    Original languageEnglish
    Pages (from-to)356-368
    Number of pages13
    JournalNeurocomputing
    Volume397
    DOIs
    Publication statusPublished - 15 Jul 2020

    Keywords

    • Adaptive algorithms
    • Adversarial setting
    • Decision-theoretic online learning
    • Delayed feedback
    • Experts problem
    • Hedging
    • Non-replicating algorithms

    Fingerprint

    Dive into the research topics of 'Adaptive hedging under delayed feedback'. Together they form a unique fingerprint.

    Cite this