ePrints@IIScePrints@IISc Home | About | Browse | Latest Additions | Advanced Search | Contact | Help

Battle of bandits

Saha, A and Gopalan, A (2018) Battle of bandits. In: 34th Conference on Uncertainty in Artificial Intelligence 2018, UAI 2018, 6 - 10 August 2018, Monterey, pp. 805-814.

Full text not available from this repository.
Official URL: https://www.auai.org/uai2018/accepted.php#top


We introduce Battling-Bandits - an online learning framework where given a set of n arms, the learner needs to select a subset of k > 2 arms in each round and subsequently observes a stochastic feedback indicating the winner of the round. This framework generalizes the standard Dueling-Bandit framework which applies to several practical scenarios such as medical treatment preferences, recommender systems, search engine optimization etc., where it is easier and more effective to collect feedback for multiple options simultaneously. We develop a novel class of pairwise-subset choice model, for modelling the subset-wise winner feedback and propose three algorithms - Battling-Doubler, Battling-MultiSBM and Battling-Duel: While the first two are designed for a special class of linear-link based choice models, the third one applies to a much general class of pairwise-subset choice models with Condorcet winner. We also analyzed their regret guarantees and show the optimality of Battling-Duel proving a matching regret lower bound of Ω(nlogT), which (perhaps surprisingly) shows that the flexibility of playing size-k subsets does not really help to gather information faster than the corresponding dueling case (k = 2), at least for the current subsetwise feedback choice model. The efficacy of our algorithms are demonstrated through extensive experimental evaluations on a variety of synthetic and real world datasets.

Item Type: Conference Paper
Publication: 34th Conference on Uncertainty in Artificial Intelligence 2018, UAI 2018
Publisher: Association For Uncertainty in Artificial Intelligence (AUAI)
Additional Information: The copyright for this article belongs to the Association For Uncertainty in Artificial Intelligence (AUAI).
Keywords: Artificial intelligence; Search engines; Stochastic systems, Condorcet winner; Experimental evaluation; General class; Medical treatment; Online learning; Real-world datasets; Search engine optimizations; Special class, Set theory
Department/Centre: Division of Electrical Sciences > Computer Science & Automation
Division of Electrical Sciences > Electrical Communication Engineering
Date Deposited: 22 Aug 2022 10:35
Last Modified: 22 Aug 2022 10:35
URI: https://eprints.iisc.ac.in/id/eprint/75964

Actions (login required)

View Item View Item