931 resultados para Internal temporal order
Filtro por publicador
- KUPS-Datenbank - Universität zu Köln - Kölner UniversitätsPublikationsServer (2)
- Academic Archive On-line (Jönköping University; Sweden) (1)
- Acceda, el repositorio institucional de la Universidad de Las Palmas de Gran Canaria. España (3)
- Adam Mickiewicz University Repository (1)
- AMS Tesi di Dottorato - Alm@DL - Università di Bologna (4)
- AMS Tesi di Laurea - Alm@DL - Università di Bologna (2)
- Aquatic Commons (4)
- ArchiMeD - Elektronische Publikationen der Universität Mainz - Alemanha (7)
- Archimer: Archive de l'Institut francais de recherche pour l'exploitation de la mer (1)
- Archive of European Integration (3)
- Archivo Digital para la Docencia y la Investigación - Repositorio Institucional de la Universidad del País Vasco (3)
- Aston University Research Archive (13)
- Biblioteca Digital | Sistema Integrado de Documentación | UNCuyo - UNCUYO. UNIVERSIDAD NACIONAL DE CUYO. (1)
- Biblioteca Digital da Produção Intelectual da Universidade de São Paulo (11)
- Biblioteca Digital da Produção Intelectual da Universidade de São Paulo (BDPI/USP) (3)
- Biblioteca Digital de la Universidad Católica Argentina (1)
- Biblioteca Digital de Teses e Dissertações Eletrônicas da UERJ (3)
- Bioline International (2)
- BORIS: Bern Open Repository and Information System - Berna - Suiça (21)
- Boston University Digital Common (8)
- Brock University, Canada (1)
- Bucknell University Digital Commons - Pensilvania - USA (2)
- Bulgarian Digital Mathematics Library at IMI-BAS (2)
- CaltechTHESIS (3)
- Cambridge University Engineering Department Publications Database (5)
- CamPuce - an association for the promotion of science and humanities in African Countries (1)
- CentAUR: Central Archive University of Reading - UK (15)
- Chinese Academy of Sciences Institutional Repositories Grid Portal (18)
- Cochin University of Science & Technology (CUSAT), India (1)
- Collection Of Biostatistics Research Archive (1)
- CORA - Cork Open Research Archive - University College Cork - Ireland (3)
- Corvinus Research Archive - The institutional repository for the Corvinus University of Budapest (1)
- Dalarna University College Electronic Archive (2)
- Deakin Research Online - Australia (17)
- Department of Computer Science E-Repository - King's College London, Strand, London (8)
- Digital Commons - Michigan Tech (3)
- Digital Commons at Florida International University (4)
- Digital Peer Publishing (1)
- DigitalCommons@The Texas Medical Center (2)
- DigitalCommons@University of Nebraska - Lincoln (2)
- DRUM (Digital Repository at the University of Maryland) (3)
- Duke University (3)
- eResearch Archive - Queensland Department of Agriculture; Fisheries and Forestry (1)
- Glasgow Theses Service (1)
- Greenwich Academic Literature Archive - UK (5)
- Helda - Digital Repository of University of Helsinki (5)
- Helvia: Repositorio Institucional de la Universidad de Córdoba (1)
- Indian Institute of Science - Bangalore - Índia (19)
- Instituto Gulbenkian de Ciência (1)
- Instituto Politécnico do Porto, Portugal (4)
- Lume - Repositório Digital da Universidade Federal do Rio Grande do Sul (1)
- National Center for Biotechnology Information - NCBI (11)
- Plymouth Marine Science Electronic Archive (PlyMSEA) (4)
- Publishing Network for Geoscientific & Environmental Data (5)
- QUB Research Portal - Research Directory and Institutional Repository for Queen's University Belfast (23)
- Queensland University of Technology - ePrints Archive (492)
- RCAAP - Repositório Científico de Acesso Aberto de Portugal (1)
- REPOSITÓRIO ABERTO do Instituto Superior Miguel Torga - Portugal (1)
- Repositório Alice (Acesso Livre à Informação Científica da Embrapa / Repository Open Access to Scientific Information from Embrapa) (3)
- Repositório Científico da Universidade de Évora - Portugal (2)
- Repositório Científico do Instituto Politécnico de Lisboa - Portugal (2)
- Repositório digital da Fundação Getúlio Vargas - FGV (2)
- Repositório Institucional da Universidade de Aveiro - Portugal (3)
- Repositório Institucional da Universidade de Brasília (1)
- Repositório Institucional da Universidade Federal do Rio Grande do Norte (1)
- Repositório Institucional UNESP - Universidade Estadual Paulista "Julio de Mesquita Filho" (53)
- RUN (Repositório da Universidade Nova de Lisboa) - FCT (Faculdade de Cienecias e Technologia), Universidade Nova de Lisboa (UNL), Portugal (3)
- Scientific Open-access Literature Archive and Repository (2)
- South Carolina State Documents Depository (1)
- Universidad de Alicante (8)
- Universidad del Rosario, Colombia (3)
- Universidad Politécnica de Madrid (19)
- Universidade Complutense de Madrid (6)
- Universidade de Lisboa - Repositório Aberto (5)
- Universidade dos Açores - Portugal (1)
- Universidade Federal do Pará (8)
- Universidade Federal do Rio Grande do Norte (UFRN) (10)
- Universitat de Girona, Spain (3)
- Universitätsbibliothek Kassel, Universität Kassel, Germany (2)
- Université de Lausanne, Switzerland (3)
- Université de Montréal (1)
- Université de Montréal, Canada (9)
- Université Laval Mémoires et thèses électroniques (1)
- University of Canberra Research Repository - Australia (1)
- University of Michigan (2)
- University of Queensland eSpace - Australia (6)
- University of Washington (2)
- Worcester Research and Publications - Worcester Research and Publications - UK (1)
Resumo:
We aim to design strategies for sequential decision making that adjust to the difficulty of the learning problem. We study this question both in the setting of prediction with expert advice, and for more general combinatorial decision tasks. We are not satisfied with just guaranteeing minimax regret rates, but we want our algorithms to perform significantly better on easy data. Two popular ways to formalize such adaptivity are second-order regret bounds and quantile bounds. The underlying notions of 'easy data', which may be paraphrased as "the learning problem has small variance" and "multiple decisions are useful", are synergetic. But even though there are sophisticated algorithms that exploit one of the two, no existing algorithm is able to adapt to both. In this paper we outline a new method for obtaining such adaptive algorithms, based on a potential function that aggregates a range of learning rates (which are essential tuning parameters). By choosing the right prior we construct efficient algorithms and show that they reap both benefits by proving the first bounds that are both second-order and incorporate quantiles.