Matches in SemOpenAlex for { <https://semopenalex.org/work/W4287028634> ?p ?o ?g. }
Showing items 1 to 67 of
67
with 100 items per page.
- W4287028634 abstract "We consider statistical methods which invoke a min-max distributionally robust formulation to extract good out-of-sample performance in data-driven optimization and learning problems. Acknowledging the distributional uncertainty in learning from limited samples, the min-max formulations introduce an adversarial inner player to explore unseen covariate data. The resulting Distributionally Robust Optimization (DRO) formulations, which include Wasserstein DRO formulations (our main focus), are specified using optimal transportation phenomena. Upon describing how these infinite-dimensional min-max problems can be approached via a finite-dimensional dual reformulation, the tutorial moves into its main component, namely, explaining a generic recipe for optimally selecting the size of the adversary's budget. This is achieved by studying the limit behavior of an optimal transport projection formulation arising from an inquiry on the smallest confidence region that includes the unknown population risk minimizer. Incidentally, this systematic prescription coincides with those in specific examples in high-dimensional statistics and results in error bounds that are free from the curse of dimensions. Equipped with this prescription, we present a central limit theorem for the DRO estimator and provide a recipe for constructing compatible confidence regions that are useful for uncertainty quantification. The rest of the tutorial is devoted to insights into the nature of the optimizers selected by the min-max formulations and additional applications of optimal transport projections." @default.
- W4287028634 created "2022-07-25" @default.
- W4287028634 creator A5011147039 @default.
- W4287028634 creator A5016557516 @default.
- W4287028634 creator A5031354096 @default.
- W4287028634 date "2021-08-04" @default.
- W4287028634 modified "2023-09-27" @default.
- W4287028634 title "Statistical Analysis of Wasserstein Distributionally Robust Estimators" @default.
- W4287028634 doi "https://doi.org/10.48550/arxiv.2108.02120" @default.
- W4287028634 hasPublicationYear "2021" @default.
- W4287028634 type Work @default.
- W4287028634 citedByCount "0" @default.
- W4287028634 crossrefType "posted-content" @default.
- W4287028634 hasAuthorship W4287028634A5011147039 @default.
- W4287028634 hasAuthorship W4287028634A5016557516 @default.
- W4287028634 hasAuthorship W4287028634A5031354096 @default.
- W4287028634 hasBestOaLocation W42870286341 @default.
- W4287028634 hasConcept C105795698 @default.
- W4287028634 hasConcept C11413529 @default.
- W4287028634 hasConcept C120665830 @default.
- W4287028634 hasConcept C121332964 @default.
- W4287028634 hasConcept C126255220 @default.
- W4287028634 hasConcept C134306372 @default.
- W4287028634 hasConcept C144024400 @default.
- W4287028634 hasConcept C149923435 @default.
- W4287028634 hasConcept C151201525 @default.
- W4287028634 hasConcept C185429906 @default.
- W4287028634 hasConcept C192209626 @default.
- W4287028634 hasConcept C193254401 @default.
- W4287028634 hasConcept C28826006 @default.
- W4287028634 hasConcept C2908647359 @default.
- W4287028634 hasConcept C33923547 @default.
- W4287028634 hasConcept C41008148 @default.
- W4287028634 hasConcept C57493831 @default.
- W4287028634 hasConceptScore W4287028634C105795698 @default.
- W4287028634 hasConceptScore W4287028634C11413529 @default.
- W4287028634 hasConceptScore W4287028634C120665830 @default.
- W4287028634 hasConceptScore W4287028634C121332964 @default.
- W4287028634 hasConceptScore W4287028634C126255220 @default.
- W4287028634 hasConceptScore W4287028634C134306372 @default.
- W4287028634 hasConceptScore W4287028634C144024400 @default.
- W4287028634 hasConceptScore W4287028634C149923435 @default.
- W4287028634 hasConceptScore W4287028634C151201525 @default.
- W4287028634 hasConceptScore W4287028634C185429906 @default.
- W4287028634 hasConceptScore W4287028634C192209626 @default.
- W4287028634 hasConceptScore W4287028634C193254401 @default.
- W4287028634 hasConceptScore W4287028634C28826006 @default.
- W4287028634 hasConceptScore W4287028634C2908647359 @default.
- W4287028634 hasConceptScore W4287028634C33923547 @default.
- W4287028634 hasConceptScore W4287028634C41008148 @default.
- W4287028634 hasConceptScore W4287028634C57493831 @default.
- W4287028634 hasLocation W42870286341 @default.
- W4287028634 hasOpenAccess W4287028634 @default.
- W4287028634 hasPrimaryLocation W42870286341 @default.
- W4287028634 hasRelatedWork W1929383332 @default.
- W4287028634 hasRelatedWork W1964781732 @default.
- W4287028634 hasRelatedWork W1973573083 @default.
- W4287028634 hasRelatedWork W1988224349 @default.
- W4287028634 hasRelatedWork W1999189895 @default.
- W4287028634 hasRelatedWork W2036654869 @default.
- W4287028634 hasRelatedWork W2045590034 @default.
- W4287028634 hasRelatedWork W2145205888 @default.
- W4287028634 hasRelatedWork W2152704622 @default.
- W4287028634 hasRelatedWork W2153822684 @default.
- W4287028634 isParatext "false" @default.
- W4287028634 isRetracted "false" @default.
- W4287028634 workType "article" @default.