Matches in SemOpenAlex for { <https://semopenalex.org/work/W3113759878> ?p ?o ?g. }
Showing items 1 to 69 of
69
with 100 items per page.
- W3113759878 abstract "Comparing and matching probability distributions is a crucial in numerous machine learning (ML) algorithms. Optimal transport (OT) defines divergences between distributions that are grounded on geometry: starting from a cost function on the underlying space, OT consists in finding a mapping or coupling between both measures that is optimal with respect to that cost. The fact that OT is deeply grounded in geometry makes it particularly well suited to ML. Further, OT is the object of a rich mathematical theory. Despite those advantages, the applications of OT in data sciences have long been hindered by the mathematical and computational complexities of the underlying optimization problem. To circumvent these issues, one approach consists in focusing on particular cases that admit closed-form solutions or that can be efficiently solved. In particular, OT between elliptical distributions is one of the very few instances for which OT is available in closed form, defining the so-called Bures-Wasserstein (BW) geometry. This thesis builds extensively on the BW geometry, with the aim to use it as basic tool in data science applications. To do so, we consider settings in which it is alternatively employed as a basic tool for representation learning, enhanced using subspace projections, and smoothed further using entropic regularization. In a first contribution, the BW geometry is used to define embeddings as elliptical probability distributions, extending on the classical representation of data as vectors in R^d.In the second contribution, we prove the existence of transportation maps and plans that extrapolate maps restricted to lower-dimensional projections, and show that subspace-optimal plans admit closed forms in the case of Gaussian measures.Our third contribution consists in deriving closed forms for entropic OT between Gaussian measures scaled with a varying total mass, which constitute the first non-trivial closed forms for entropic OT and provide the first continuous test case for the study of entropic OT. Finally, in a last contribution, entropic OT is leveraged to tackle missing data imputation in a non-parametric and distribution-preserving way." @default.
- W3113759878 created "2021-01-05" @default.
- W3113759878 creator A5004431423 @default.
- W3113759878 date "2020-10-26" @default.
- W3113759878 modified "2023-09-27" @default.
- W3113759878 title "Leveraging regularization, projections and elliptical distributions in optimal transport" @default.
- W3113759878 hasPublicationYear "2020" @default.
- W3113759878 type Work @default.
- W3113759878 sameAs 3113759878 @default.
- W3113759878 citedByCount "0" @default.
- W3113759878 crossrefType "dissertation" @default.
- W3113759878 hasAuthorship W3113759878A5004431423 @default.
- W3113759878 hasConcept C105795698 @default.
- W3113759878 hasConcept C11413529 @default.
- W3113759878 hasConcept C126255220 @default.
- W3113759878 hasConcept C149441793 @default.
- W3113759878 hasConcept C154945302 @default.
- W3113759878 hasConcept C17744445 @default.
- W3113759878 hasConcept C199539241 @default.
- W3113759878 hasConcept C2524010 @default.
- W3113759878 hasConcept C2776135515 @default.
- W3113759878 hasConcept C2776359362 @default.
- W3113759878 hasConcept C32834561 @default.
- W3113759878 hasConcept C33923547 @default.
- W3113759878 hasConcept C41008148 @default.
- W3113759878 hasConcept C80444323 @default.
- W3113759878 hasConcept C94625758 @default.
- W3113759878 hasConceptScore W3113759878C105795698 @default.
- W3113759878 hasConceptScore W3113759878C11413529 @default.
- W3113759878 hasConceptScore W3113759878C126255220 @default.
- W3113759878 hasConceptScore W3113759878C149441793 @default.
- W3113759878 hasConceptScore W3113759878C154945302 @default.
- W3113759878 hasConceptScore W3113759878C17744445 @default.
- W3113759878 hasConceptScore W3113759878C199539241 @default.
- W3113759878 hasConceptScore W3113759878C2524010 @default.
- W3113759878 hasConceptScore W3113759878C2776135515 @default.
- W3113759878 hasConceptScore W3113759878C2776359362 @default.
- W3113759878 hasConceptScore W3113759878C32834561 @default.
- W3113759878 hasConceptScore W3113759878C33923547 @default.
- W3113759878 hasConceptScore W3113759878C41008148 @default.
- W3113759878 hasConceptScore W3113759878C80444323 @default.
- W3113759878 hasConceptScore W3113759878C94625758 @default.
- W3113759878 hasLocation W31137598781 @default.
- W3113759878 hasOpenAccess W3113759878 @default.
- W3113759878 hasPrimaryLocation W31137598781 @default.
- W3113759878 hasRelatedWork W1738112110 @default.
- W3113759878 hasRelatedWork W2123235230 @default.
- W3113759878 hasRelatedWork W2172478671 @default.
- W3113759878 hasRelatedWork W2758533541 @default.
- W3113759878 hasRelatedWork W2944818408 @default.
- W3113759878 hasRelatedWork W2946472767 @default.
- W3113759878 hasRelatedWork W2949235510 @default.
- W3113759878 hasRelatedWork W2964172337 @default.
- W3113759878 hasRelatedWork W2964259376 @default.
- W3113759878 hasRelatedWork W3017057773 @default.
- W3113759878 hasRelatedWork W3037176388 @default.
- W3113759878 hasRelatedWork W3080088097 @default.
- W3113759878 hasRelatedWork W3093545757 @default.
- W3113759878 hasRelatedWork W3106114912 @default.
- W3113759878 hasRelatedWork W3129083736 @default.
- W3113759878 hasRelatedWork W3134184365 @default.
- W3113759878 hasRelatedWork W3153274218 @default.
- W3113759878 hasRelatedWork W3165102544 @default.
- W3113759878 hasRelatedWork W3171809359 @default.
- W3113759878 hasRelatedWork W3213496558 @default.
- W3113759878 isParatext "false" @default.
- W3113759878 isRetracted "false" @default.
- W3113759878 magId "3113759878" @default.
- W3113759878 workType "dissertation" @default.