Matches in SemOpenAlex for { <https://semopenalex.org/work/W4293342911> ?p ?o ?g. }
Showing items 1 to 53 of
53
with 100 items per page.
- W4293342911 abstract "Wasserstein-Fisher-Rao (WFR) distance is a family of metrics to gauge the discrepancy of two Radon measures, which takes into account both transportation and weight change. Spherical WFR distance is a projected version of WFR distance for probability measures so that the space of Radon measures equipped with WFR can be viewed as metric cone over the space of probability measures with spherical WFR. Compared to the case for Wasserstein distance, the understanding of geodesics under the spherical WFR is less clear and still an ongoing research focus. In this paper, we develop a deep learning framework to compute the geodesics under the spherical WFR metric, and the learned geodesics can be adopted to generate weighted samples. Our approach is based on a Benamou-Brenier type dynamic formulation for spherical WFR. To overcome the difficulty in enforcing the boundary constraint brought by the weight change, a Kullback-Leibler (KL) divergence term based on the inverse map is introduced into the cost function. Moreover, a new regularization term using the particle velocity is introduced as a substitute for the Hamilton-Jacobi equation for the potential in dynamic formula. When used for sample generation, our framework can be beneficial for applications with given weighted samples, especially in the Bayesian inference, compared to sample generation with previous flow models." @default.
- W4293342911 created "2022-08-27" @default.
- W4293342911 creator A5061472917 @default.
- W4293342911 creator A5067651647 @default.
- W4293342911 creator A5075889094 @default.
- W4293342911 creator A5089860286 @default.
- W4293342911 date "2022-08-25" @default.
- W4293342911 modified "2023-10-16" @default.
- W4293342911 title "A deep learning framework for geodesics under spherical Wasserstein-Fisher-Rao metric and its application for weighted sample generation" @default.
- W4293342911 doi "https://doi.org/10.48550/arxiv.2208.12145" @default.
- W4293342911 hasPublicationYear "2022" @default.
- W4293342911 type Work @default.
- W4293342911 citedByCount "0" @default.
- W4293342911 crossrefType "posted-content" @default.
- W4293342911 hasAuthorship W4293342911A5061472917 @default.
- W4293342911 hasAuthorship W4293342911A5067651647 @default.
- W4293342911 hasAuthorship W4293342911A5075889094 @default.
- W4293342911 hasAuthorship W4293342911A5089860286 @default.
- W4293342911 hasBestOaLocation W42933429111 @default.
- W4293342911 hasConcept C134306372 @default.
- W4293342911 hasConcept C162324750 @default.
- W4293342911 hasConcept C165818556 @default.
- W4293342911 hasConcept C176217482 @default.
- W4293342911 hasConcept C21547014 @default.
- W4293342911 hasConcept C2777634741 @default.
- W4293342911 hasConcept C28826006 @default.
- W4293342911 hasConcept C33923547 @default.
- W4293342911 hasConcept C62354387 @default.
- W4293342911 hasConceptScore W4293342911C134306372 @default.
- W4293342911 hasConceptScore W4293342911C162324750 @default.
- W4293342911 hasConceptScore W4293342911C165818556 @default.
- W4293342911 hasConceptScore W4293342911C176217482 @default.
- W4293342911 hasConceptScore W4293342911C21547014 @default.
- W4293342911 hasConceptScore W4293342911C2777634741 @default.
- W4293342911 hasConceptScore W4293342911C28826006 @default.
- W4293342911 hasConceptScore W4293342911C33923547 @default.
- W4293342911 hasConceptScore W4293342911C62354387 @default.
- W4293342911 hasLocation W42933429111 @default.
- W4293342911 hasOpenAccess W4293342911 @default.
- W4293342911 hasPrimaryLocation W42933429111 @default.
- W4293342911 hasRelatedWork W1741548419 @default.
- W4293342911 hasRelatedWork W2172478671 @default.
- W4293342911 hasRelatedWork W2951649716 @default.
- W4293342911 hasRelatedWork W2952213070 @default.
- W4293342911 hasRelatedWork W2953307913 @default.
- W4293342911 hasRelatedWork W2997064483 @default.
- W4293342911 hasRelatedWork W3106244882 @default.
- W4293342911 hasRelatedWork W4226279395 @default.
- W4293342911 hasRelatedWork W4289754235 @default.
- W4293342911 hasRelatedWork W4301181598 @default.
- W4293342911 isParatext "false" @default.
- W4293342911 isRetracted "false" @default.
- W4293342911 workType "article" @default.