• About
  • Policies
  • What is open access
  • Library
  • Contact
Advanced search
      View Item 
      •   BUIR Home
      • Scholarly Publications
      • Faculty of Engineering
      • Department of Electrical and Electronics Engineering
      • View Item
      •   BUIR Home
      • Scholarly Publications
      • Faculty of Engineering
      • Department of Electrical and Electronics Engineering
      • View Item
      JavaScript is disabled for your browser. Some features of this site may not work without it.

      RELEAF: an algorithm for learning and exploiting relevance

      Thumbnail
      View / Download
      311.5 Kb
      Author(s)
      Tekin, C.
      Schaar, Mihaela van der
      Date
      2015-02
      Source Title
      IEEE Journal of Selected Topics in Signal Processing
      Publisher
      Cornell University
      Pages
      1 - 15
      Language
      English
      Type
      Article
      Item Usage Stats
      100
      views
      83
      downloads
      Abstract
      Recommender systems, medical diagnosis, network security, etc., require on-going learning and decision-making in real time. These -- and many others -- represent perfect examples of the opportunities and difficulties presented by Big Data: the available information often arrives from a variety of sources and has diverse features so that learning from all the sources may be valuable but integrating what is learned is subject to the curse of dimensionality. This paper develops and analyzes algorithms that allow efficient learning and decision-making while avoiding the curse of dimensionality. We formalize the information available to the learner/decision-maker at a particular time as a context vector which the learner should consider when taking actions. In general the context vector is very high dimensional, but in many settings, the most relevant information is embedded into only a few relevant dimensions. If these relevant dimensions were known in advance, the problem would be simple -- but they are not. Moreover, the relevant dimensions may be different for different actions. Our algorithm learns the relevant dimensions for each action, and makes decisions based in what it has learned. Formally, we build on the structure of a contextual multi-armed bandit by adding and exploiting a relevance relation. We prove a general regret bound for our algorithm whose time order depends only on the maximum number of relevant dimensions among all the actions, which in the special case where the relevance relation is single-valued (a function), reduces to O~(T2(2√−1)); in the absence of a relevance relation, the best known contextual bandit algorithms achieve regret O~(T(D+1)/(D+2)), where D is the full dimension of the context vector.
      Keywords
      Contextual bandits
      Regret
      Dimensionality reduction
      Learning relevance
      Recommender systems
      Online learning
      Active learning
      Permalink
      http://hdl.handle.net/11693/49374
      Collections
      • Department of Electrical and Electronics Engineering 3702
      Show full item record

      Browse

      All of BUIRCommunities & CollectionsTitlesAuthorsAdvisorsBy Issue DateKeywordsTypeDepartmentsThis CollectionTitlesAuthorsAdvisorsBy Issue DateKeywordsTypeDepartments

      My Account

      LoginRegister

      Statistics

      View Usage StatisticsView Google Analytics Statistics

      Bilkent University

      If you have trouble accessing this page and need to request an alternate format, contact the site administrator. Phone: (312) 290 1771
      © Bilkent University - Library IT

      Contact Us | Send Feedback | Off-Campus Access | Admin | Privacy