Matches in SemOpenAlex for { <https://semopenalex.org/work/W2914003818> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W2914003818 endingPage "5081" @default.
- W2914003818 startingPage "5072" @default.
- W2914003818 abstract "Making sense of Wasserstein distances between discrete measures in high-dimensional settings remains a challenge. Recent work has advocated a two-step approach to improve robustness and facilitate the computation of optimal transport, using for instance projections on random real lines, or a preliminary quantization of the measures to reduce the size of their support. We propose in this work a max-min robust variant of the Wasserstein distance by considering the maximal possible distance that can be realized between two measures, assuming they can be projected orthogonally on a lower $k$-dimensional subspace. Alternatively, we show that the corresponding min-max OT problem has a tight convex relaxation which can be cast as that of finding an optimal transport plan with a low transportation cost, where the cost is alternatively defined as the sum of the $k$ largest eigenvalues of the second order moment matrix of the displacements (or matchings) corresponding to that plan (the usual OT definition only considers the trace of that matrix). We show that both quantities inherit several favorable properties from the OT geometry. We propose two algorithms to compute the latter formulation using entropic regularization, and illustrate the interest of this approach empirically." @default.
- W2914003818 created "2019-02-21" @default.
- W2914003818 creator A5002436541 @default.
- W2914003818 creator A5017263427 @default.
- W2914003818 date "2019-05-24" @default.
- W2914003818 modified "2023-09-28" @default.
- W2914003818 title "Subspace Robust Wasserstein Distances" @default.
- W2914003818 hasPublicationYear "2019" @default.
- W2914003818 type Work @default.
- W2914003818 sameAs 2914003818 @default.
- W2914003818 citedByCount "48" @default.
- W2914003818 countsByYear W29140038182019 @default.
- W2914003818 countsByYear W29140038182020 @default.
- W2914003818 countsByYear W29140038182021 @default.
- W2914003818 countsByYear W29140038182022 @default.
- W2914003818 crossrefType "proceedings-article" @default.
- W2914003818 hasAuthorship W2914003818A5002436541 @default.
- W2914003818 hasAuthorship W2914003818A5017263427 @default.
- W2914003818 hasConcept C104317684 @default.
- W2914003818 hasConcept C112680207 @default.
- W2914003818 hasConcept C11413529 @default.
- W2914003818 hasConcept C121332964 @default.
- W2914003818 hasConcept C126255220 @default.
- W2914003818 hasConcept C134306372 @default.
- W2914003818 hasConcept C158693339 @default.
- W2914003818 hasConcept C185592680 @default.
- W2914003818 hasConcept C2524010 @default.
- W2914003818 hasConcept C28826006 @default.
- W2914003818 hasConcept C32834561 @default.
- W2914003818 hasConcept C33923547 @default.
- W2914003818 hasConcept C41008148 @default.
- W2914003818 hasConcept C45374587 @default.
- W2914003818 hasConcept C55493867 @default.
- W2914003818 hasConcept C62520636 @default.
- W2914003818 hasConcept C63479239 @default.
- W2914003818 hasConceptScore W2914003818C104317684 @default.
- W2914003818 hasConceptScore W2914003818C112680207 @default.
- W2914003818 hasConceptScore W2914003818C11413529 @default.
- W2914003818 hasConceptScore W2914003818C121332964 @default.
- W2914003818 hasConceptScore W2914003818C126255220 @default.
- W2914003818 hasConceptScore W2914003818C134306372 @default.
- W2914003818 hasConceptScore W2914003818C158693339 @default.
- W2914003818 hasConceptScore W2914003818C185592680 @default.
- W2914003818 hasConceptScore W2914003818C2524010 @default.
- W2914003818 hasConceptScore W2914003818C28826006 @default.
- W2914003818 hasConceptScore W2914003818C32834561 @default.
- W2914003818 hasConceptScore W2914003818C33923547 @default.
- W2914003818 hasConceptScore W2914003818C41008148 @default.
- W2914003818 hasConceptScore W2914003818C45374587 @default.
- W2914003818 hasConceptScore W2914003818C55493867 @default.
- W2914003818 hasConceptScore W2914003818C62520636 @default.
- W2914003818 hasConceptScore W2914003818C63479239 @default.
- W2914003818 hasLocation W29140038181 @default.
- W2914003818 hasOpenAccess W2914003818 @default.
- W2914003818 hasPrimaryLocation W29140038181 @default.
- W2914003818 hasRelatedWork W1594039573 @default.
- W2914003818 hasRelatedWork W1639961155 @default.
- W2914003818 hasRelatedWork W2019106840 @default.
- W2914003818 hasRelatedWork W2037468546 @default.
- W2914003818 hasRelatedWork W2158131535 @default.
- W2914003818 hasRelatedWork W2739748921 @default.
- W2914003818 hasRelatedWork W2793477525 @default.
- W2914003818 hasRelatedWork W2895248218 @default.
- W2914003818 hasRelatedWork W2907366006 @default.
- W2914003818 hasRelatedWork W2952493076 @default.
- W2914003818 hasRelatedWork W2962879692 @default.
- W2914003818 hasRelatedWork W2962970351 @default.
- W2914003818 hasRelatedWork W2963134136 @default.
- W2914003818 hasRelatedWork W2963398989 @default.
- W2914003818 hasRelatedWork W2963506485 @default.
- W2914003818 hasRelatedWork W2963563295 @default.
- W2914003818 hasRelatedWork W2964308809 @default.
- W2914003818 hasRelatedWork W2970112944 @default.
- W2914003818 hasRelatedWork W2979557588 @default.
- W2914003818 hasRelatedWork W786520459 @default.
- W2914003818 isParatext "false" @default.
- W2914003818 isRetracted "false" @default.
- W2914003818 magId "2914003818" @default.
- W2914003818 workType "article" @default.