1 resultado para quasi-stationary
em Massachusetts Institute of Technology
Filtro por publicador
- KUPS-Datenbank - Universität zu Köln - Kölner UniversitätsPublikationsServer (1)
- Aberystwyth University Repository - Reino Unido (3)
- Academic Archive On-line (Karlstad University; Sweden) (1)
- Academic Research Repository at Institute of Developing Economies (1)
- Acceda, el repositorio institucional de la Universidad de Las Palmas de Gran Canaria. España (1)
- AMS Tesi di Dottorato - Alm@DL - Università di Bologna (3)
- AMS Tesi di Laurea - Alm@DL - Università di Bologna (9)
- Aquatic Commons (4)
- ArchiMeD - Elektronische Publikationen der Universität Mainz - Alemanha (2)
- Archimer: Archive de l'Institut francais de recherche pour l'exploitation de la mer (3)
- Archive of European Integration (2)
- Archivo Digital para la Docencia y la Investigación - Repositorio Institucional de la Universidad del País Vasco (6)
- Aston University Research Archive (53)
- Biblioteca Digital da Produção Intelectual da Universidade de São Paulo (19)
- Biblioteca Digital da Produção Intelectual da Universidade de São Paulo (BDPI/USP) (26)
- Biblioteca Digital Loyola - Universidad de Deusto (4)
- BORIS: Bern Open Repository and Information System - Berna - Suiça (38)
- Boston University Digital Common (1)
- Brock University, Canada (5)
- Brunel University (1)
- Bulgarian Digital Mathematics Library at IMI-BAS (19)
- CaltechTHESIS (9)
- Cambridge University Engineering Department Publications Database (55)
- CentAUR: Central Archive University of Reading - UK (70)
- Chinese Academy of Sciences Institutional Repositories Grid Portal (126)
- Cochin University of Science & Technology (CUSAT), India (4)
- Coffee Science - Universidade Federal de Lavras (3)
- Comissão Econômica para a América Latina e o Caribe (CEPAL) (4)
- CORA - Cork Open Research Archive - University College Cork - Ireland (3)
- Corvinus Research Archive - The institutional repository for the Corvinus University of Budapest (2)
- Dalarna University College Electronic Archive (3)
- Deakin Research Online - Australia (43)
- Digital Commons at Florida International University (4)
- Digital Peer Publishing (1)
- DigitalCommons - The University of Maine Research (1)
- DigitalCommons@The Texas Medical Center (1)
- Digitale Sammlungen - Goethe-Universität Frankfurt am Main (2)
- DRUM (Digital Repository at the University of Maryland) (1)
- Duke University (2)
- Fachlicher Dokumentenserver Paedagogik/Erziehungswissenschaften (1)
- FUNDAJ - Fundação Joaquim Nabuco (2)
- Gallica, Bibliotheque Numerique - Bibliothèque nationale de France (French National Library) (BnF), France (5)
- Greenwich Academic Literature Archive - UK (3)
- Harvard University (1)
- Helda - Digital Repository of University of Helsinki (4)
- Indian Institute of Science - Bangalore - Índia (81)
- Institutional Repository of Leibniz University Hannover (1)
- INSTITUTO DE PESQUISAS ENERGÉTICAS E NUCLEARES (IPEN) - Repositório Digital da Produção Técnico Científica - BibliotecaTerezine Arantes Ferra (2)
- Instituto Politécnico do Porto, Portugal (1)
- Instituto Superior de Psicologia Aplicada - Lisboa (1)
- Massachusetts Institute of Technology (1)
- Ministerio de Cultura, Spain (2)
- National Center for Biotechnology Information - NCBI (9)
- Nottingham eTheses (1)
- Plymouth Marine Science Electronic Archive (PlyMSEA) (3)
- Publishing Network for Geoscientific & Environmental Data (9)
- QUB Research Portal - Research Directory and Institutional Repository for Queen's University Belfast (68)
- Queensland University of Technology - ePrints Archive (43)
- Repositório Científico da Universidade de Évora - Portugal (2)
- Repositório digital da Fundação Getúlio Vargas - FGV (8)
- Repositório Digital da UNIVERSIDADE DA MADEIRA - Portugal (1)
- Repositório Institucional da Universidade de Aveiro - Portugal (2)
- Repositório Institucional da Universidade de Brasília (1)
- Repositório Institucional UNESP - Universidade Estadual Paulista "Julio de Mesquita Filho" (56)
- Research Open Access Repository of the University of East London. (1)
- RUN (Repositório da Universidade Nova de Lisboa) - FCT (Faculdade de Cienecias e Technologia), Universidade Nova de Lisboa (UNL), Portugal (2)
- SAPIENTIA - Universidade do Algarve - Portugal (1)
- Savoirs UdeS : plateforme de diffusion de la production intellectuelle de l’Université de Sherbrooke - Canada (1)
- Universidad de Alicante (6)
- Universidad del Rosario, Colombia (1)
- Universidad Politécnica de Madrid (21)
- Universidade Complutense de Madrid (5)
- Universidade de Lisboa - Repositório Aberto (1)
- Universidade Estadual Paulista "Júlio de Mesquita Filho" (UNESP) (1)
- Universidade Federal do Pará (1)
- Universidade Federal do Rio Grande do Norte (UFRN) (4)
- Universita di Parma (1)
- Universitat de Girona, Spain (3)
- Universitätsbibliothek Kassel, Universität Kassel, Germany (6)
- Université de Lausanne, Switzerland (2)
- Université de Montréal (1)
- Université de Montréal, Canada (13)
- Université Laval Mémoires et thèses électroniques (1)
- University of Connecticut - USA (2)
- University of Michigan (37)
- University of Queensland eSpace - Australia (30)
- Worcester Research and Publications - Worcester Research and Publications - UK (1)
Resumo:
We consider an online learning scenario in which the learner can make predictions on the basis of a fixed set of experts. The performance of each expert may change over time in a manner unknown to the learner. We formulate a class of universal learning algorithms for this problem by expressing them as simple Bayesian algorithms operating on models analogous to Hidden Markov Models (HMMs). We derive a new performance bound for such algorithms which is considerably simpler than existing bounds. The bound provides the basis for learning the rate at which the identity of the optimal expert switches over time. We find an analytic expression for the a priori resolution at which we need to learn the rate parameter. We extend our scalar switching-rate result to models of the switching-rate that are governed by a matrix of parameters, i.e. arbitrary homogeneous HMMs. We apply and examine our algorithm in the context of the problem of energy management in wireless networks. We analyze the new results in the framework of Information Theory.