Matches in SemOpenAlex for { <https://semopenalex.org/work/W4214925787> ?p ?o ?g. }
Showing items 1 to 97 of
97
with 100 items per page.
- W4214925787 abstract "Many problems in the physical sciences, machine learning, and statistical inference necessitate sampling from a high-dimensional, multi-modal probability distribution. Markov Chain Monte Carlo (MCMC) algorithms, the ubiquitous tool for this task, typically rely on random local updates to propagate configurations of a given system in a way that ensures that generated configurations will be distributed according to a target probability distribution asymptotically. In high-dimensional settings with multiple relevant metastable basins, local approaches require either immense computational effort or intricately designed importance sampling strategies to capture information about, for example, the relative populations of such basins. Here we analyze an adaptive MCMC which augments MCMC sampling with nonlocal transition kernels parameterized with generative models known as normalizing flows. We focus on a setting where there is no preexisting data, as is commonly the case for problems in which MCMC is used. Our method uses: (i) a MCMC strategy that blends local moves obtained from any standard transition kernel with those from a generative model to accelerate the sampling and (ii) the data generated this way to adapt the generative model and improve its efficacy in the MCMC algorithm. We provide a theoretical analysis of the convergence properties of this algorithm, and investigate numerically its efficiency, in particular in terms of its propensity to equilibrate fast between metastable modes whose rough location is known textit{a~priori} but respective probability weight is not. We show that our algorithm can sample effectively across large free energy barriers, providing dramatic accelerations relative to traditional MCMC algorithms." @default.
- W4214925787 created "2022-03-05" @default.
- W4214925787 creator A5001522727 @default.
- W4214925787 creator A5044193587 @default.
- W4214925787 creator A5071403558 @default.
- W4214925787 date "2022-03-02" @default.
- W4214925787 modified "2023-10-05" @default.
- W4214925787 title "Adaptive Monte Carlo augmented with normalizing flows" @default.
- W4214925787 cites W1585160083 @default.
- W4214925787 cites W1983452151 @default.
- W4214925787 cites W1995780830 @default.
- W4214925787 cites W2010288972 @default.
- W4214925787 cites W2064871928 @default.
- W4214925787 cites W2099490136 @default.
- W4214925787 cites W2148178414 @default.
- W4214925787 cites W2338816311 @default.
- W4214925787 cites W2530117613 @default.
- W4214925787 cites W2893674448 @default.
- W4214925787 cites W2941443959 @default.
- W4214925787 cites W2972246420 @default.
- W4214925787 cites W3006106210 @default.
- W4214925787 cites W3029632440 @default.
- W4214925787 cites W3042241440 @default.
- W4214925787 cites W3080219767 @default.
- W4214925787 cites W3099467939 @default.
- W4214925787 cites W3122343732 @default.
- W4214925787 cites W3133146080 @default.
- W4214925787 cites W3189986861 @default.
- W4214925787 cites W3214514905 @default.
- W4214925787 cites W4255839052 @default.
- W4214925787 cites W83924355 @default.
- W4214925787 doi "https://doi.org/10.1073/pnas.2109420119" @default.
- W4214925787 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35235453" @default.
- W4214925787 hasPublicationYear "2022" @default.
- W4214925787 type Work @default.
- W4214925787 citedByCount "21" @default.
- W4214925787 countsByYear W42149257872022 @default.
- W4214925787 countsByYear W42149257872023 @default.
- W4214925787 crossrefType "journal-article" @default.
- W4214925787 hasAuthorship W4214925787A5001522727 @default.
- W4214925787 hasAuthorship W4214925787A5044193587 @default.
- W4214925787 hasAuthorship W4214925787A5071403558 @default.
- W4214925787 hasBestOaLocation W42149257871 @default.
- W4214925787 hasConcept C105795698 @default.
- W4214925787 hasConcept C106131492 @default.
- W4214925787 hasConcept C107673813 @default.
- W4214925787 hasConcept C111350023 @default.
- W4214925787 hasConcept C11413529 @default.
- W4214925787 hasConcept C126255220 @default.
- W4214925787 hasConcept C13153151 @default.
- W4214925787 hasConcept C140779682 @default.
- W4214925787 hasConcept C154945302 @default.
- W4214925787 hasConcept C170593435 @default.
- W4214925787 hasConcept C187192777 @default.
- W4214925787 hasConcept C19499675 @default.
- W4214925787 hasConcept C31972630 @default.
- W4214925787 hasConcept C33923547 @default.
- W4214925787 hasConcept C41008148 @default.
- W4214925787 hasConcept C52740198 @default.
- W4214925787 hasConceptScore W4214925787C105795698 @default.
- W4214925787 hasConceptScore W4214925787C106131492 @default.
- W4214925787 hasConceptScore W4214925787C107673813 @default.
- W4214925787 hasConceptScore W4214925787C111350023 @default.
- W4214925787 hasConceptScore W4214925787C11413529 @default.
- W4214925787 hasConceptScore W4214925787C126255220 @default.
- W4214925787 hasConceptScore W4214925787C13153151 @default.
- W4214925787 hasConceptScore W4214925787C140779682 @default.
- W4214925787 hasConceptScore W4214925787C154945302 @default.
- W4214925787 hasConceptScore W4214925787C170593435 @default.
- W4214925787 hasConceptScore W4214925787C187192777 @default.
- W4214925787 hasConceptScore W4214925787C19499675 @default.
- W4214925787 hasConceptScore W4214925787C31972630 @default.
- W4214925787 hasConceptScore W4214925787C33923547 @default.
- W4214925787 hasConceptScore W4214925787C41008148 @default.
- W4214925787 hasConceptScore W4214925787C52740198 @default.
- W4214925787 hasIssue "10" @default.
- W4214925787 hasLocation W42149257871 @default.
- W4214925787 hasLocation W42149257872 @default.
- W4214925787 hasLocation W42149257873 @default.
- W4214925787 hasLocation W42149257874 @default.
- W4214925787 hasLocation W42149257875 @default.
- W4214925787 hasOpenAccess W4214925787 @default.
- W4214925787 hasPrimaryLocation W42149257871 @default.
- W4214925787 hasRelatedWork W1593554773 @default.
- W4214925787 hasRelatedWork W2031427063 @default.
- W4214925787 hasRelatedWork W2033057584 @default.
- W4214925787 hasRelatedWork W2036896164 @default.
- W4214925787 hasRelatedWork W2922027001 @default.
- W4214925787 hasRelatedWork W2948895238 @default.
- W4214925787 hasRelatedWork W2983001628 @default.
- W4214925787 hasRelatedWork W3097509027 @default.
- W4214925787 hasRelatedWork W4287691656 @default.
- W4214925787 hasRelatedWork W4295750535 @default.
- W4214925787 hasVolume "119" @default.
- W4214925787 isParatext "false" @default.
- W4214925787 isRetracted "false" @default.
- W4214925787 workType "article" @default.