Matches in SemOpenAlex for { <https://semopenalex.org/work/W3204206070> ?p ?o ?g. }
- W3204206070 abstract "This paper introduces a new simulation-based inference procedure to model and sample from multi-dimensional probability distributions given access to i.i.d. samples, circumventing the usual approaches of explicitly modeling the density function or designing Markov chain Monte Carlo. Motivated by the seminal work on distance and isomorphism between metric measure spaces, we propose a new notion called the Reversible Gromov-Monge (RGM) distance and study how RGM can be used to design new transform samplers to perform simulation-based inference. Our RGM sampler can also estimate optimal alignments between two heterogeneous metric measure spaces $(cX, mu, c_{cX})$ and $(cY, nu, c_{cY})$ from empirical data sets, with estimated maps that approximately push forward one measure $mu$ to the other $nu$, and vice versa. We study the analytic properties of the RGM distance and derive that under mild conditions, RGM equals the classic Gromov-Wasserstein distance. Curiously, drawing a connection to Brenier's polar factorization, we show that the RGM sampler induces bias towards strong isomorphism with proper choices of $c_{cX}$ and $c_{cY}$. Statistical rate of convergence, representation, and optimization questions regarding the induced sampler are studied. Synthetic and real-world examples showcasing the effectiveness of the RGM sampler are also demonstrated." @default.
- W3204206070 created "2021-10-11" @default.
- W3204206070 creator A5035404367 @default.
- W3204206070 creator A5038333857 @default.
- W3204206070 creator A5082274064 @default.
- W3204206070 date "2021-09-28" @default.
- W3204206070 modified "2023-09-23" @default.
- W3204206070 title "Reversible Gromov-Monge Sampler for Simulation-Based Inference" @default.
- W3204206070 cites W1482513167 @default.
- W3204206070 cites W1487641199 @default.
- W3204206070 cites W1511139817 @default.
- W3204206070 cites W1542886316 @default.
- W3204206070 cites W1571975558 @default.
- W3204206070 cites W1985093013 @default.
- W3204206070 cites W2000992741 @default.
- W3204206070 cites W2005747881 @default.
- W3204206070 cites W2019302713 @default.
- W3204206070 cites W2027842533 @default.
- W3204206070 cites W2038845890 @default.
- W3204206070 cites W2099471712 @default.
- W3204206070 cites W2121035504 @default.
- W3204206070 cites W2129905273 @default.
- W3204206070 cites W2132883347 @default.
- W3204206070 cites W2292609460 @default.
- W3204206070 cites W2417433140 @default.
- W3204206070 cites W2467604901 @default.
- W3204206070 cites W2474265885 @default.
- W3204206070 cites W2596625124 @default.
- W3204206070 cites W2739748921 @default.
- W3204206070 cites W2765094320 @default.
- W3204206070 cites W2787877872 @default.
- W3204206070 cites W2810203579 @default.
- W3204206070 cites W2912099989 @default.
- W3204206070 cites W2912286675 @default.
- W3204206070 cites W2951004968 @default.
- W3204206070 cites W2952745707 @default.
- W3204206070 cites W2963647223 @default.
- W3204206070 cites W2963690839 @default.
- W3204206070 cites W2963800509 @default.
- W3204206070 cites W2964121744 @default.
- W3204206070 cites W2980328027 @default.
- W3204206070 cites W2986904542 @default.
- W3204206070 cites W2991210238 @default.
- W3204206070 cites W3005398290 @default.
- W3204206070 cites W3022007431 @default.
- W3204206070 cites W3081116588 @default.
- W3204206070 cites W3101183984 @default.
- W3204206070 cites W3121235808 @default.
- W3204206070 cites W568673721 @default.
- W3204206070 cites W930928758 @default.
- W3204206070 doi "https://doi.org/10.48550/arxiv.2109.14090" @default.
- W3204206070 hasPublicationYear "2021" @default.
- W3204206070 type Work @default.
- W3204206070 sameAs 3204206070 @default.
- W3204206070 citedByCount "0" @default.
- W3204206070 crossrefType "posted-content" @default.
- W3204206070 hasAuthorship W3204206070A5035404367 @default.
- W3204206070 hasAuthorship W3204206070A5038333857 @default.
- W3204206070 hasAuthorship W3204206070A5082274064 @default.
- W3204206070 hasBestOaLocation W32042060701 @default.
- W3204206070 hasConcept C105795698 @default.
- W3204206070 hasConcept C111350023 @default.
- W3204206070 hasConcept C111919701 @default.
- W3204206070 hasConcept C11413529 @default.
- W3204206070 hasConcept C118615104 @default.
- W3204206070 hasConcept C124101348 @default.
- W3204206070 hasConcept C134261354 @default.
- W3204206070 hasConcept C14036430 @default.
- W3204206070 hasConcept C154945302 @default.
- W3204206070 hasConcept C162324750 @default.
- W3204206070 hasConcept C176217482 @default.
- W3204206070 hasConcept C17744445 @default.
- W3204206070 hasConcept C19499675 @default.
- W3204206070 hasConcept C198043062 @default.
- W3204206070 hasConcept C199539241 @default.
- W3204206070 hasConcept C21031990 @default.
- W3204206070 hasConcept C21547014 @default.
- W3204206070 hasConcept C2776214188 @default.
- W3204206070 hasConcept C2776359362 @default.
- W3204206070 hasConcept C2777303404 @default.
- W3204206070 hasConcept C2778572836 @default.
- W3204206070 hasConcept C2780009758 @default.
- W3204206070 hasConcept C28826006 @default.
- W3204206070 hasConcept C33923547 @default.
- W3204206070 hasConcept C41008148 @default.
- W3204206070 hasConcept C50522688 @default.
- W3204206070 hasConcept C78458016 @default.
- W3204206070 hasConcept C86803240 @default.
- W3204206070 hasConcept C94625758 @default.
- W3204206070 hasConcept C98763669 @default.
- W3204206070 hasConceptScore W3204206070C105795698 @default.
- W3204206070 hasConceptScore W3204206070C111350023 @default.
- W3204206070 hasConceptScore W3204206070C111919701 @default.
- W3204206070 hasConceptScore W3204206070C11413529 @default.
- W3204206070 hasConceptScore W3204206070C118615104 @default.
- W3204206070 hasConceptScore W3204206070C124101348 @default.
- W3204206070 hasConceptScore W3204206070C134261354 @default.
- W3204206070 hasConceptScore W3204206070C14036430 @default.
- W3204206070 hasConceptScore W3204206070C154945302 @default.
- W3204206070 hasConceptScore W3204206070C162324750 @default.