Matches in SemOpenAlex for { <https://semopenalex.org/work/W4308609496> ?p ?o ?g. }
Showing items 1 to 47 of
47
with 100 items per page.
- W4308609496 abstract "We study the unbalanced optimal transport (UOT) problem, where the marginal constraints are enforced using Maximum Mean Discrepancy (MMD) regularization. Our work is motivated by the observation that the literature on UOT is focused on regularization based on $phi$-divergence (e.g., KL divergence). Despite the popularity of MMD, its role as a regularizer in the context of UOT seems less understood. We begin by deriving a specific dual of MMD-regularized UOT (MMD-UOT), which helps us prove several useful properties. One interesting outcome of this duality result is that MMD-UOT induces novel metrics, which not only lift the ground metric like the Wasserstein but are also sample-wise efficient to estimate like the MMD. Further, for real-world applications involving non-discrete measures, we present an estimator for the transport plan that is supported only on the given ($m$) samples. Under mild conditions, we prove that the estimation error with this finitely-supported transport plan is also $mathcal{O}(1/sqrt{m})$. As far as we know, such error bounds that are free from the curse of dimensionality are not known for $phi$-divergence regularized UOT. Finally, we discuss how the proposed estimator can be computed efficiently using accelerated gradient descent. Our experiments show that MMD-UOT consistently outperforms popular baselines, including KL-regularized UOT and MMD, in diverse machine learning applications." @default.
- W4308609496 created "2022-11-13" @default.
- W4308609496 creator A5015809185 @default.
- W4308609496 creator A5081803338 @default.
- W4308609496 creator A5086696547 @default.
- W4308609496 date "2020-11-10" @default.
- W4308609496 modified "2023-09-23" @default.
- W4308609496 title "MMD-Regularized Unbalanced Optimal Transport" @default.
- W4308609496 doi "https://doi.org/10.48550/arxiv.2011.05001" @default.
- W4308609496 hasPublicationYear "2020" @default.
- W4308609496 type Work @default.
- W4308609496 citedByCount "0" @default.
- W4308609496 crossrefType "posted-content" @default.
- W4308609496 hasAuthorship W4308609496A5015809185 @default.
- W4308609496 hasAuthorship W4308609496A5081803338 @default.
- W4308609496 hasAuthorship W4308609496A5086696547 @default.
- W4308609496 hasBestOaLocation W43086094961 @default.
- W4308609496 hasConcept C105795698 @default.
- W4308609496 hasConcept C154945302 @default.
- W4308609496 hasConcept C185429906 @default.
- W4308609496 hasConcept C2776135515 @default.
- W4308609496 hasConcept C28826006 @default.
- W4308609496 hasConcept C33923547 @default.
- W4308609496 hasConcept C41008148 @default.
- W4308609496 hasConceptScore W4308609496C105795698 @default.
- W4308609496 hasConceptScore W4308609496C154945302 @default.
- W4308609496 hasConceptScore W4308609496C185429906 @default.
- W4308609496 hasConceptScore W4308609496C2776135515 @default.
- W4308609496 hasConceptScore W4308609496C28826006 @default.
- W4308609496 hasConceptScore W4308609496C33923547 @default.
- W4308609496 hasConceptScore W4308609496C41008148 @default.
- W4308609496 hasLocation W43086094961 @default.
- W4308609496 hasOpenAccess W4308609496 @default.
- W4308609496 hasPrimaryLocation W43086094961 @default.
- W4308609496 hasRelatedWork W1493561834 @default.
- W4308609496 hasRelatedWork W1988224349 @default.
- W4308609496 hasRelatedWork W2111483792 @default.
- W4308609496 hasRelatedWork W2158914562 @default.
- W4308609496 hasRelatedWork W2236763869 @default.
- W4308609496 hasRelatedWork W2292176388 @default.
- W4308609496 hasRelatedWork W2295159760 @default.
- W4308609496 hasRelatedWork W2906277522 @default.
- W4308609496 hasRelatedWork W3124794310 @default.
- W4308609496 hasRelatedWork W4245953108 @default.
- W4308609496 isParatext "false" @default.
- W4308609496 isRetracted "false" @default.
- W4308609496 workType "article" @default.