FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3201737995> ?p ?o ?g. }

• W3201737995 abstract "Optimal transport (OT) is a powerful geometric tool for comparing two distributions and has been employed in various machine learning applications. In this work, we propose a novel OT formulation that takes feature correlations into account while learning the transport plan between two distributions. We model the feature-feature relationship via a symmetric positive semi-definite Mahalanobis metric in the OT cost function. For a certain class of regularizers on the metric, we show that the optimization strategy can be considerably simplified by exploiting the problem structure. For high-dimensional data, we additionally propose suitable low-dimensional modeling of the Mahalanobis metric. Overall, we view the resulting optimization problem as a non-linear OT problem, which we solve using the Frank-Wolfe algorithm. Empirical results on the discriminative learning setting, such as tag prediction and multi-class classification, illustrate the good performance of our approach." @default.
• W3201737995 created "2021-10-11" @default.
• W3201737995 creator A5023551959 @default.
• W3201737995 creator A5079928272 @default.
• W3201737995 creator A5086696547 @default.
• W3201737995 date "2021-12-14" @default.
• W3201737995 modified "2023-09-23" @default.
• W3201737995 title "Efficient Robust Optimal Transport with Application to Multi-Label Classification" @default.
• W3201737995 cites W1568307856 @default.
• W3201737995 cites W1963882359 @default.
• W3201737995 cites W1985077192 @default.
• W3201737995 cites W2079639858 @default.
• W3201737995 cites W2093357278 @default.
• W3201737995 cites W2118840614 @default.
• W3201737995 cites W2131116400 @default.
• W3201737995 cites W2134270519 @default.
• W3201737995 cites W2143668817 @default.
• W3201737995 cites W2153579005 @default.
• W3201737995 cites W2158131535 @default.
• W3201737995 cites W2161997479 @default.
• W3201737995 cites W2176791116 @default.
• W3201737995 cites W2211574168 @default.
• W3201737995 cites W2250384498 @default.
• W3201737995 cites W2493916176 @default.
• W3201737995 cites W2515212212 @default.
• W3201737995 cites W2739748921 @default.
• W3201737995 cites W2786130756 @default.
• W3201737995 cites W2793477525 @default.
• W3201737995 cites W2798766386 @default.
• W3201737995 cites W2804284765 @default.
• W3201737995 cites W2914003818 @default.
• W3201737995 cites W2936342412 @default.
• W3201737995 cites W2962997028 @default.
• W3201737995 cites W2963472233 @default.
• W3201737995 cites W2963506485 @default.
• W3201737995 cites W2964272353 @default.
• W3201737995 cites W2970112944 @default.
• W3201737995 cites W3009330671 @default.
• W3201737995 cites W3026401092 @default.
• W3201737995 cites W3035286614 @default.
• W3201737995 cites W3035295418 @default.
• W3201737995 cites W3035391512 @default.
• W3201737995 cites W3202905720 @default.
• W3201737995 cites W562660536 @default.
• W3201737995 cites W905619 @default.
• W3201737995 doi "https://doi.org/10.1109/cdc45484.2021.9683259" @default.
• W3201737995 hasPublicationYear "2021" @default.
• W3201737995 type Work @default.
• W3201737995 sameAs 3201737995 @default.
• W3201737995 citedByCount "0" @default.
• W3201737995 crossrefType "proceedings-article" @default.
• W3201737995 hasAuthorship W3201737995A5023551959 @default.
• W3201737995 hasAuthorship W3201737995A5079928272 @default.
• W3201737995 hasAuthorship W3201737995A5086696547 @default.
• W3201737995 hasBestOaLocation W32017379952 @default.
• W3201737995 hasConcept C11413529 @default.
• W3201737995 hasConcept C119857082 @default.
• W3201737995 hasConcept C126255220 @default.
• W3201737995 hasConcept C127413603 @default.
• W3201737995 hasConcept C137836250 @default.
• W3201737995 hasConcept C138885662 @default.
• W3201737995 hasConcept C153180895 @default.
• W3201737995 hasConcept C154945302 @default.
• W3201737995 hasConcept C176217482 @default.
• W3201737995 hasConcept C1921717 @default.
• W3201737995 hasConcept C21547014 @default.
• W3201737995 hasConcept C2776401178 @default.
• W3201737995 hasConcept C2777212361 @default.
• W3201737995 hasConcept C33923547 @default.
• W3201737995 hasConcept C41008148 @default.
• W3201737995 hasConcept C41895202 @default.
• W3201737995 hasConcept C97931131 @default.
• W3201737995 hasConceptScore W3201737995C11413529 @default.
• W3201737995 hasConceptScore W3201737995C119857082 @default.
• W3201737995 hasConceptScore W3201737995C126255220 @default.
• W3201737995 hasConceptScore W3201737995C127413603 @default.
• W3201737995 hasConceptScore W3201737995C137836250 @default.
• W3201737995 hasConceptScore W3201737995C138885662 @default.
• W3201737995 hasConceptScore W3201737995C153180895 @default.
• W3201737995 hasConceptScore W3201737995C154945302 @default.
• W3201737995 hasConceptScore W3201737995C176217482 @default.
• W3201737995 hasConceptScore W3201737995C1921717 @default.
• W3201737995 hasConceptScore W3201737995C21547014 @default.
• W3201737995 hasConceptScore W3201737995C2776401178 @default.
• W3201737995 hasConceptScore W3201737995C2777212361 @default.
• W3201737995 hasConceptScore W3201737995C33923547 @default.
• W3201737995 hasConceptScore W3201737995C41008148 @default.
• W3201737995 hasConceptScore W3201737995C41895202 @default.
• W3201737995 hasConceptScore W3201737995C97931131 @default.
• W3201737995 hasLocation W32017379951 @default.
• W3201737995 hasLocation W32017379952 @default.
• W3201737995 hasOpenAccess W3201737995 @default.
• W3201737995 hasPrimaryLocation W32017379951 @default.
• W3201737995 hasRelatedWork W1652783584 @default.
• W3201737995 hasRelatedWork W1971623867 @default.
• W3201737995 hasRelatedWork W1982770690 @default.
• W3201737995 hasRelatedWork W2006158573 @default.
• W3201737995 hasRelatedWork W2024160000 @default.
• W3201737995 hasRelatedWork W2345231148 @default.
• W3201737995 hasRelatedWork W2404514746 @default.

• next