Online learning with noisy side observations
Document type :
Communication dans un congrès avec actes
Title :
Online learning with noisy side observations
Author(s) :
Kocák, Tomáš [Auteur]
Sequential Learning [SEQUEL]
Neu, Gergely [Auteur]
Sequential Learning [SEQUEL]
Valko, Michal [Auteur]
Sequential Learning [SEQUEL]
Sequential Learning [SEQUEL]
Neu, Gergely [Auteur]
Sequential Learning [SEQUEL]
Valko, Michal [Auteur]
Sequential Learning [SEQUEL]
Conference title :
International Conference on Artificial Intelligence and Statistics
City :
Seville
Country :
Espagne
Start date of the conference :
2016-05-09
HAL domain(s) :
Statistiques [stat]/Machine Learning [stat.ML]
English abstract : [en]
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 ...
Show more >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.Show less >
Show more >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.Show less >
Language :
Anglais
Peer reviewed article :
Oui
Audience :
Internationale
Popular science :
Non
Collections :
Source :
Files
- https://hal.inria.fr/hal-01303377/document
- Open access
- Access the document
- https://hal.inria.fr/hal-01303377/document
- Open access
- Access the document
- https://hal.inria.fr/hal-01303377/document
- Open access
- Access the document
- document
- Open access
- Access the document
- kocak2016online.pdf
- Open access
- Access the document