Matches in SemOpenAlex for { <https://semopenalex.org/work/W4320165504> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W4320165504 abstract "Despite the recent success of representation learning in sequential decision making, the study of the pure exploration scenario (i.e., identify the best option and minimize the sample complexity) is still limited. In this paper, we study multi-task representation learning for best arm identification in linear bandits (RepBAI-LB) and best policy identification in contextual linear bandits (RepBPI-CLB), two popular pure exploration settings with wide applications, e.g., clinical trials and web content optimization. In these two problems, all tasks share a common low-dimensional linear representation, and our goal is to leverage this feature to accelerate the best arm (policy) identification process for all tasks. For these problems, we design computationally and sample efficient algorithms DouExpDes and C-DouExpDes, which perform double experimental designs to plan optimal sample allocations for learning the global representation. We show that by learning the common representation among tasks, our sample complexity is significantly better than that of the native approach which solves tasks independently. To the best of our knowledge, this is the first work to demonstrate the benefits of representation learning for multi-task pure exploration." @default.
- W4320165504 created "2023-02-13" @default.
- W4320165504 creator A5054293823 @default.
- W4320165504 creator A5082905458 @default.
- W4320165504 creator A5084629039 @default.
- W4320165504 date "2023-02-09" @default.
- W4320165504 modified "2023-09-29" @default.
- W4320165504 title "Multi-task Representation Learning for Pure Exploration in Linear Bandits" @default.
- W4320165504 doi "https://doi.org/10.48550/arxiv.2302.04441" @default.
- W4320165504 hasPublicationYear "2023" @default.
- W4320165504 type Work @default.
- W4320165504 citedByCount "0" @default.
- W4320165504 crossrefType "posted-content" @default.
- W4320165504 hasAuthorship W4320165504A5054293823 @default.
- W4320165504 hasAuthorship W4320165504A5082905458 @default.
- W4320165504 hasAuthorship W4320165504A5084629039 @default.
- W4320165504 hasBestOaLocation W43201655041 @default.
- W4320165504 hasConcept C116834253 @default.
- W4320165504 hasConcept C119857082 @default.
- W4320165504 hasConcept C138885662 @default.
- W4320165504 hasConcept C153083717 @default.
- W4320165504 hasConcept C154945302 @default.
- W4320165504 hasConcept C162324750 @default.
- W4320165504 hasConcept C17744445 @default.
- W4320165504 hasConcept C185592680 @default.
- W4320165504 hasConcept C187736073 @default.
- W4320165504 hasConcept C198531522 @default.
- W4320165504 hasConcept C199539241 @default.
- W4320165504 hasConcept C2776359362 @default.
- W4320165504 hasConcept C2776401178 @default.
- W4320165504 hasConcept C2778445095 @default.
- W4320165504 hasConcept C2780451532 @default.
- W4320165504 hasConcept C28006648 @default.
- W4320165504 hasConcept C41008148 @default.
- W4320165504 hasConcept C41895202 @default.
- W4320165504 hasConcept C43617362 @default.
- W4320165504 hasConcept C59404180 @default.
- W4320165504 hasConcept C59822182 @default.
- W4320165504 hasConcept C86803240 @default.
- W4320165504 hasConcept C94625758 @default.
- W4320165504 hasConceptScore W4320165504C116834253 @default.
- W4320165504 hasConceptScore W4320165504C119857082 @default.
- W4320165504 hasConceptScore W4320165504C138885662 @default.
- W4320165504 hasConceptScore W4320165504C153083717 @default.
- W4320165504 hasConceptScore W4320165504C154945302 @default.
- W4320165504 hasConceptScore W4320165504C162324750 @default.
- W4320165504 hasConceptScore W4320165504C17744445 @default.
- W4320165504 hasConceptScore W4320165504C185592680 @default.
- W4320165504 hasConceptScore W4320165504C187736073 @default.
- W4320165504 hasConceptScore W4320165504C198531522 @default.
- W4320165504 hasConceptScore W4320165504C199539241 @default.
- W4320165504 hasConceptScore W4320165504C2776359362 @default.
- W4320165504 hasConceptScore W4320165504C2776401178 @default.
- W4320165504 hasConceptScore W4320165504C2778445095 @default.
- W4320165504 hasConceptScore W4320165504C2780451532 @default.
- W4320165504 hasConceptScore W4320165504C28006648 @default.
- W4320165504 hasConceptScore W4320165504C41008148 @default.
- W4320165504 hasConceptScore W4320165504C41895202 @default.
- W4320165504 hasConceptScore W4320165504C43617362 @default.
- W4320165504 hasConceptScore W4320165504C59404180 @default.
- W4320165504 hasConceptScore W4320165504C59822182 @default.
- W4320165504 hasConceptScore W4320165504C86803240 @default.
- W4320165504 hasConceptScore W4320165504C94625758 @default.
- W4320165504 hasLocation W43201655041 @default.
- W4320165504 hasOpenAccess W4320165504 @default.
- W4320165504 hasPrimaryLocation W43201655041 @default.
- W4320165504 hasRelatedWork W2903184186 @default.
- W4320165504 hasRelatedWork W2908875379 @default.
- W4320165504 hasRelatedWork W3001496086 @default.
- W4320165504 hasRelatedWork W3098365587 @default.
- W4320165504 hasRelatedWork W3155211092 @default.
- W4320165504 hasRelatedWork W3211269067 @default.
- W4320165504 hasRelatedWork W4224014834 @default.
- W4320165504 hasRelatedWork W4289147925 @default.
- W4320165504 hasRelatedWork W4320165504 @default.
- W4320165504 hasRelatedWork W4366399932 @default.
- W4320165504 isParatext "false" @default.
- W4320165504 isRetracted "false" @default.
- W4320165504 workType "article" @default.