Matches in SemOpenAlex for { <https://semopenalex.org/work/W2181750757> ?p ?o ?g. }
Showing items 1 to 82 of
82
with 100 items per page.
- W2181750757 abstract "Multi-task learning can be shown to improve the generalization performance of single tasks under certain conditions. Typically, the algorithmic and theoretical analysis of multi-task learning deals with a two-level structure, including a group of tasks and a single task. In many situations, however, it is benecial to consider varying degrees of relatedness among tasks, assuming that some tasks are closely related and should contribute more to the learning process, while other tasks are less related but can still contribute some information to the learning process. The extension of current approaches to the multi-level setting may not be trivial. We propose a general framework for a full hierarchical multi-task setting. We dene an explicit notion of hierarchical tasks relatedness, where at each level we assume that some aspects of the learning problem are shared. We suggest a cascade approach, where at each level of the hierarchy a learner learns jointly the uniquely shared aspects of the tasks by nding a single shared hypothesis. This shared hypothesis is used to bootstrap the preceding level in the hierarchy, forming a hypothesis search space. We analyze sufcient conditions for our approach to reach optimality, and provide generalization guarantees in an empirical risk minimization setting." @default.
- W2181750757 created "2016-06-24" @default.
- W2181750757 creator A5000206190 @default.
- W2181750757 creator A5087543513 @default.
- W2181750757 date "2013-01-01" @default.
- W2181750757 modified "2023-09-26" @default.
- W2181750757 title "Hierarchical Multi-Task Learning: a Cascade Approach Based on the Notion of Task Relatedness" @default.
- W2181750757 cites W1988520084 @default.
- W2181750757 cites W1994022788 @default.
- W2181750757 cites W2019363670 @default.
- W2181750757 cites W2040852548 @default.
- W2181750757 cites W2131479143 @default.
- W2181750757 cites W2138745909 @default.
- W2181750757 cites W2144752499 @default.
- W2181750757 cites W2150766729 @default.
- W2181750757 cites W2913340405 @default.
- W2181750757 cites W2962839807 @default.
- W2181750757 cites W2964121793 @default.
- W2181750757 cites W2974222084 @default.
- W2181750757 hasPublicationYear "2013" @default.
- W2181750757 type Work @default.
- W2181750757 sameAs 2181750757 @default.
- W2181750757 citedByCount "1" @default.
- W2181750757 countsByYear W21817507572020 @default.
- W2181750757 crossrefType "journal-article" @default.
- W2181750757 hasAuthorship W2181750757A5000206190 @default.
- W2181750757 hasAuthorship W2181750757A5087543513 @default.
- W2181750757 hasConcept C111919701 @default.
- W2181750757 hasConcept C119857082 @default.
- W2181750757 hasConcept C134306372 @default.
- W2181750757 hasConcept C154945302 @default.
- W2181750757 hasConcept C162324750 @default.
- W2181750757 hasConcept C177148314 @default.
- W2181750757 hasConcept C187736073 @default.
- W2181750757 hasConcept C2780451532 @default.
- W2181750757 hasConcept C28006648 @default.
- W2181750757 hasConcept C31170391 @default.
- W2181750757 hasConcept C33923547 @default.
- W2181750757 hasConcept C34447519 @default.
- W2181750757 hasConcept C41008148 @default.
- W2181750757 hasConcept C98045186 @default.
- W2181750757 hasConceptScore W2181750757C111919701 @default.
- W2181750757 hasConceptScore W2181750757C119857082 @default.
- W2181750757 hasConceptScore W2181750757C134306372 @default.
- W2181750757 hasConceptScore W2181750757C154945302 @default.
- W2181750757 hasConceptScore W2181750757C162324750 @default.
- W2181750757 hasConceptScore W2181750757C177148314 @default.
- W2181750757 hasConceptScore W2181750757C187736073 @default.
- W2181750757 hasConceptScore W2181750757C2780451532 @default.
- W2181750757 hasConceptScore W2181750757C28006648 @default.
- W2181750757 hasConceptScore W2181750757C31170391 @default.
- W2181750757 hasConceptScore W2181750757C33923547 @default.
- W2181750757 hasConceptScore W2181750757C34447519 @default.
- W2181750757 hasConceptScore W2181750757C41008148 @default.
- W2181750757 hasConceptScore W2181750757C98045186 @default.
- W2181750757 hasLocation W21817507571 @default.
- W2181750757 hasOpenAccess W2181750757 @default.
- W2181750757 hasPrimaryLocation W21817507571 @default.
- W2181750757 hasRelatedWork W1536749735 @default.
- W2181750757 hasRelatedWork W1567876833 @default.
- W2181750757 hasRelatedWork W2061304498 @default.
- W2181750757 hasRelatedWork W2147198965 @default.
- W2181750757 hasRelatedWork W2150287743 @default.
- W2181750757 hasRelatedWork W2266522507 @default.
- W2181750757 hasRelatedWork W2340940935 @default.
- W2181750757 hasRelatedWork W2397132841 @default.
- W2181750757 hasRelatedWork W2408113697 @default.
- W2181750757 hasRelatedWork W2557804916 @default.
- W2181750757 hasRelatedWork W2899291363 @default.
- W2181750757 hasRelatedWork W295306427 @default.
- W2181750757 hasRelatedWork W2989834192 @default.
- W2181750757 hasRelatedWork W2998653237 @default.
- W2181750757 hasRelatedWork W3003482291 @default.
- W2181750757 hasRelatedWork W3032908123 @default.
- W2181750757 hasRelatedWork W3100676560 @default.
- W2181750757 hasRelatedWork W3108607087 @default.
- W2181750757 hasRelatedWork W3131881724 @default.
- W2181750757 hasRelatedWork W3099111597 @default.
- W2181750757 isParatext "false" @default.
- W2181750757 isRetracted "false" @default.
- W2181750757 magId "2181750757" @default.
- W2181750757 workType "article" @default.