Skip to Main content Skip to Navigation
Conference papers

Online learning with noisy side observations

Tomáš Kocák 1 Gergely Neu 2, 1 Michal Valko 1
1 SEQUEL - Sequential Learning
Inria Lille - Nord Europe, CRIStAL - Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189
Abstract : We propose a new partial-observability model for online learning problems where the learner, besides its own loss, also observes some noisy feedback about the other actions, depending on the underlying structure of the problem. We represent this structure by a weighted directed graph, where the edge weights are related to the quality of the feedback shared by the connected nodes. Our main contribution is an efficient algorithm that guarantees a regret of O(√ α * T) after T rounds, where α * is a novel graph property that we call the effective independence number. Our algorithm is completely parameter-free and does not require knowledge (or even estimation) of α *. For the special case of binary edge weights, our setting reduces to the partial-observability models of Mannor & Shamir (2011) and Alon et al. (2013) and our algorithm recovers the near-optimal regret bounds.
Document type :
Conference papers
Complete list of metadata

Cited literature [14 references]  Display  Hide  Download
Contributor : Michal Valko Connect in order to contact the contributor
Submitted on : Monday, April 18, 2016 - 10:03:59 AM
Last modification on : Thursday, January 20, 2022 - 4:16:42 PM
Long-term archiving on: : Tuesday, November 15, 2016 - 4:57:07 AM


Files produced by the author(s)


  • HAL Id : hal-01303377, version 1



Tomáš Kocák, Gergely Neu, Michal Valko. Online learning with noisy side observations. International Conference on Artificial Intelligence and Statistics, May 2016, Seville, Spain. ⟨hal-01303377⟩



Les métriques sont temporairement indisponibles