Matches in SemOpenAlex for { <https://semopenalex.org/work/W4287136596> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W4287136596 abstract "Gradient flows are a powerful tool for optimizing functionals in general metric spaces, including the space of probabilities endowed with the Wasserstein metric. A typical approach to solving this optimization problem relies on its connection to the dynamic formulation of optimal transport and the celebrated Jordan-Kinderlehrer-Otto (JKO) scheme. However, this formulation involves optimization over convex functions, which is challenging, especially in high dimensions. In this work, we propose an approach that relies on the recently introduced input-convex neural networks (ICNN) to parametrize the space of convex functions in order to approximate the JKO scheme, as well as in designing functionals over measures that enjoy convergence guarantees. We derive a computationally efficient implementation of this JKO-ICNN framework and experimentally demonstrate its feasibility and validity in approximating solutions of low-dimensional partial differential equations with known solutions. We also demonstrate its viability in high-dimensional applications through an experiment in controlled generation for molecular discovery." @default.
- W4287136596 created "2022-07-25" @default.
- W4287136596 creator A5009860808 @default.
- W4287136596 creator A5024311601 @default.
- W4287136596 creator A5064636177 @default.
- W4287136596 date "2021-06-01" @default.
- W4287136596 modified "2023-09-29" @default.
- W4287136596 title "Optimizing Functionals on the Space of Probabilities with Input Convex Neural Networks" @default.
- W4287136596 doi "https://doi.org/10.48550/arxiv.2106.00774" @default.
- W4287136596 hasPublicationYear "2021" @default.
- W4287136596 type Work @default.
- W4287136596 citedByCount "0" @default.
- W4287136596 crossrefType "posted-content" @default.
- W4287136596 hasAuthorship W4287136596A5009860808 @default.
- W4287136596 hasAuthorship W4287136596A5024311601 @default.
- W4287136596 hasAuthorship W4287136596A5064636177 @default.
- W4287136596 hasBestOaLocation W42871365961 @default.
- W4287136596 hasConcept C111919701 @default.
- W4287136596 hasConcept C112680207 @default.
- W4287136596 hasConcept C12108790 @default.
- W4287136596 hasConcept C126255220 @default.
- W4287136596 hasConcept C134306372 @default.
- W4287136596 hasConcept C14036430 @default.
- W4287136596 hasConcept C145446738 @default.
- W4287136596 hasConcept C154945302 @default.
- W4287136596 hasConcept C157972887 @default.
- W4287136596 hasConcept C162324750 @default.
- W4287136596 hasConcept C176217482 @default.
- W4287136596 hasConcept C198043062 @default.
- W4287136596 hasConcept C21547014 @default.
- W4287136596 hasConcept C2524010 @default.
- W4287136596 hasConcept C2777303404 @default.
- W4287136596 hasConcept C2778572836 @default.
- W4287136596 hasConcept C28826006 @default.
- W4287136596 hasConcept C33923547 @default.
- W4287136596 hasConcept C41008148 @default.
- W4287136596 hasConcept C50522688 @default.
- W4287136596 hasConcept C50644808 @default.
- W4287136596 hasConcept C78458016 @default.
- W4287136596 hasConcept C86803240 @default.
- W4287136596 hasConceptScore W4287136596C111919701 @default.
- W4287136596 hasConceptScore W4287136596C112680207 @default.
- W4287136596 hasConceptScore W4287136596C12108790 @default.
- W4287136596 hasConceptScore W4287136596C126255220 @default.
- W4287136596 hasConceptScore W4287136596C134306372 @default.
- W4287136596 hasConceptScore W4287136596C14036430 @default.
- W4287136596 hasConceptScore W4287136596C145446738 @default.
- W4287136596 hasConceptScore W4287136596C154945302 @default.
- W4287136596 hasConceptScore W4287136596C157972887 @default.
- W4287136596 hasConceptScore W4287136596C162324750 @default.
- W4287136596 hasConceptScore W4287136596C176217482 @default.
- W4287136596 hasConceptScore W4287136596C198043062 @default.
- W4287136596 hasConceptScore W4287136596C21547014 @default.
- W4287136596 hasConceptScore W4287136596C2524010 @default.
- W4287136596 hasConceptScore W4287136596C2777303404 @default.
- W4287136596 hasConceptScore W4287136596C2778572836 @default.
- W4287136596 hasConceptScore W4287136596C28826006 @default.
- W4287136596 hasConceptScore W4287136596C33923547 @default.
- W4287136596 hasConceptScore W4287136596C41008148 @default.
- W4287136596 hasConceptScore W4287136596C50522688 @default.
- W4287136596 hasConceptScore W4287136596C50644808 @default.
- W4287136596 hasConceptScore W4287136596C78458016 @default.
- W4287136596 hasConceptScore W4287136596C86803240 @default.
- W4287136596 hasLocation W42871365961 @default.
- W4287136596 hasOpenAccess W4287136596 @default.
- W4287136596 hasPrimaryLocation W42871365961 @default.
- W4287136596 hasRelatedWork W2175532135 @default.
- W4287136596 hasRelatedWork W2371360614 @default.
- W4287136596 hasRelatedWork W2384641331 @default.
- W4287136596 hasRelatedWork W2811008754 @default.
- W4287136596 hasRelatedWork W2953109382 @default.
- W4287136596 hasRelatedWork W2956043763 @default.
- W4287136596 hasRelatedWork W3003165794 @default.
- W4287136596 hasRelatedWork W4287899549 @default.
- W4287136596 hasRelatedWork W4302370212 @default.
- W4287136596 hasRelatedWork W4377007384 @default.
- W4287136596 isParatext "false" @default.
- W4287136596 isRetracted "false" @default.
- W4287136596 workType "article" @default.