Matches in SemOpenAlex for { <https://semopenalex.org/work/W4298090544> ?p ?o ?g. }
Showing items 1 to 55 of
55
with 100 items per page.
- W4298090544 abstract "As opposed to standard empirical risk minimization (ERM), distributionally robust optimization aims to minimize the worst-case risk over a larger ambiguity set containing the original empirical distribution of the training data. In this work, we describe a minimax framework for statistical learning with ambiguity sets given by balls in Wasserstein space. In particular, we prove generalization bounds that involve the covering number properties of the original ERM problem. As an illustrative example, we provide generalization guarantees for transport-based domain adaptation problems where the Wasserstein distance between the source and target domain distributions can be reliably estimated from unlabeled samples." @default.
- W4298090544 created "2022-10-01" @default.
- W4298090544 creator A5009295669 @default.
- W4298090544 creator A5044844161 @default.
- W4298090544 date "2017-05-22" @default.
- W4298090544 modified "2023-10-16" @default.
- W4298090544 title "Minimax Statistical Learning with Wasserstein Distances" @default.
- W4298090544 doi "https://doi.org/10.48550/arxiv.1705.07815" @default.
- W4298090544 hasPublicationYear "2017" @default.
- W4298090544 type Work @default.
- W4298090544 citedByCount "0" @default.
- W4298090544 crossrefType "posted-content" @default.
- W4298090544 hasAuthorship W4298090544A5009295669 @default.
- W4298090544 hasAuthorship W4298090544A5044844161 @default.
- W4298090544 hasBestOaLocation W42980905441 @default.
- W4298090544 hasConcept C107321475 @default.
- W4298090544 hasConcept C126255220 @default.
- W4298090544 hasConcept C134306372 @default.
- W4298090544 hasConcept C147764199 @default.
- W4298090544 hasConcept C149728462 @default.
- W4298090544 hasConcept C177148314 @default.
- W4298090544 hasConcept C177264268 @default.
- W4298090544 hasConcept C199360897 @default.
- W4298090544 hasConcept C2780522230 @default.
- W4298090544 hasConcept C33923547 @default.
- W4298090544 hasConcept C36503486 @default.
- W4298090544 hasConcept C41008148 @default.
- W4298090544 hasConceptScore W4298090544C107321475 @default.
- W4298090544 hasConceptScore W4298090544C126255220 @default.
- W4298090544 hasConceptScore W4298090544C134306372 @default.
- W4298090544 hasConceptScore W4298090544C147764199 @default.
- W4298090544 hasConceptScore W4298090544C149728462 @default.
- W4298090544 hasConceptScore W4298090544C177148314 @default.
- W4298090544 hasConceptScore W4298090544C177264268 @default.
- W4298090544 hasConceptScore W4298090544C199360897 @default.
- W4298090544 hasConceptScore W4298090544C2780522230 @default.
- W4298090544 hasConceptScore W4298090544C33923547 @default.
- W4298090544 hasConceptScore W4298090544C36503486 @default.
- W4298090544 hasConceptScore W4298090544C41008148 @default.
- W4298090544 hasLocation W42980905441 @default.
- W4298090544 hasOpenAccess W4298090544 @default.
- W4298090544 hasPrimaryLocation W42980905441 @default.
- W4298090544 hasRelatedWork W2060518740 @default.
- W4298090544 hasRelatedWork W2891229686 @default.
- W4298090544 hasRelatedWork W2909950896 @default.
- W4298090544 hasRelatedWork W2953362272 @default.
- W4298090544 hasRelatedWork W2962830515 @default.
- W4298090544 hasRelatedWork W3186670436 @default.
- W4298090544 hasRelatedWork W4288634235 @default.
- W4298090544 hasRelatedWork W4298090544 @default.
- W4298090544 hasRelatedWork W4313304367 @default.
- W4298090544 hasRelatedWork W4367393663 @default.
- W4298090544 isParatext "false" @default.
- W4298090544 isRetracted "false" @default.
- W4298090544 workType "article" @default.