Algorithmic Chaining and the Role of Partial Feedback in Online Nonparametric Learning - Archive ouverte HAL Access content directly
Conference Papers Year : 2017

Algorithmic Chaining and the Role of Partial Feedback in Online Nonparametric Learning

Abstract

We investigate contextual online learning with nonparametric (Lipschitz) comparison classes under different assumptions on losses and feedback information. For full information feedback and Lipschitz losses, we design the first explicit algorithm achieving the minimax regret rate (up to log factors). In a partial feedback model motivated by second-price auctions, we obtain algorithms for Lipschitz and semi-Lipschitz losses with regret bounds improving on the known bounds for standard bandit feedback. Our analysis combines novel results for contextual second-price auctions with a novel algorithmic approach based on chaining. When the context space is Euclidean, our chaining approach is efficient and delivers an even better regret bound.
Fichier principal
Vignette du fichier
NonparametricLearning.pdf (441.15 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01476771 , version 1 (25-02-2017)
hal-01476771 , version 2 (23-06-2017)

Identifiers

Cite

Nicolò Cesa-Bianchi, Pierre Gaillard, Claudio Gentile, Sébastien Gerchinovitz. Algorithmic Chaining and the Role of Partial Feedback in Online Nonparametric Learning. COLT 2017, Jul 2017, Amsterdam, Netherlands. pp.465-481. ⟨hal-01476771v2⟩
482 View
398 Download

Altmetric

Share

Gmail Facebook X LinkedIn More