Matches in SemOpenAlex for { <https://semopenalex.org/work/W4360998918> ?p ?o ?g. }
- W4360998918 endingPage "25" @default.
- W4360998918 startingPage "1" @default.
- W4360998918 abstract "We introduce Reflective Hamiltonian Monte Carlo (ReHMC), an HMC-based algorithm, to sample from a log-concave distribution restricted to a convex body. We prove that, starting from a warm start, the walk mixes to a log-concave target distribution $pi(x) propto e^{-f(x)}$, where $f$ is $L$-smooth and $m$-strongly-convex, within accuracy $varepsilon$ after $widetilde O(kappa d^2 ell^2 log (1 / varepsilon))$ steps for a well-rounded convex body where $kappa = L / m$ is the condition number of the negative log-density, $d$ is the dimension, $ell$ is an upper bound on the number of reflections, and $varepsilon$ is the accuracy parameter. We also developed an efficient open source implementation of ReHMC and we performed an experimental study on various high-dimensional data-sets. The experiments suggest that ReHMC outperfroms Hit-and-Run and Coordinate-Hit-and-Run regarding the time it needs to produce an independent sample and introduces practical truncated sampling in thousands of dimensions." @default.
- W4360998918 created "2023-03-30" @default.
- W4360998918 creator A5002548887 @default.
- W4360998918 creator A5024426907 @default.
- W4360998918 creator A5057880103 @default.
- W4360998918 creator A5080051337 @default.
- W4360998918 date "2023-06-15" @default.
- W4360998918 modified "2023-09-30" @default.
- W4360998918 title "Truncated Log-concave Sampling for Convex Bodies with Reflective Hamiltonian Monte Carlo" @default.
- W4360998918 cites W1506380541 @default.
- W4360998918 cites W1545319692 @default.
- W4360998918 cites W1558572410 @default.
- W4360998918 cites W1559116151 @default.
- W4360998918 cites W1788547584 @default.
- W4360998918 cites W187211397 @default.
- W4360998918 cites W1979577865 @default.
- W4360998918 cites W1986001860 @default.
- W4360998918 cites W1996999318 @default.
- W4360998918 cites W2017646611 @default.
- W4360998918 cites W2019516978 @default.
- W4360998918 cites W2025334959 @default.
- W4360998918 cites W2056760934 @default.
- W4360998918 cites W2059448777 @default.
- W4360998918 cites W2063342497 @default.
- W4360998918 cites W2076125241 @default.
- W4360998918 cites W2078355959 @default.
- W4360998918 cites W2083543317 @default.
- W4360998918 cites W2088413985 @default.
- W4360998918 cites W2092264912 @default.
- W4360998918 cites W2095165504 @default.
- W4360998918 cites W2104963735 @default.
- W4360998918 cites W2108077794 @default.
- W4360998918 cites W2128585485 @default.
- W4360998918 cites W2138309709 @default.
- W4360998918 cites W2148534890 @default.
- W4360998918 cites W2159000620 @default.
- W4360998918 cites W2168908795 @default.
- W4360998918 cites W2310707124 @default.
- W4360998918 cites W2577537660 @default.
- W4360998918 cites W2583438419 @default.
- W4360998918 cites W2594846523 @default.
- W4360998918 cites W2787991113 @default.
- W4360998918 cites W2809413523 @default.
- W4360998918 cites W2896267177 @default.
- W4360998918 cites W2963060562 @default.
- W4360998918 cites W2963559717 @default.
- W4360998918 cites W2963813262 @default.
- W4360998918 cites W2967843340 @default.
- W4360998918 cites W3023788998 @default.
- W4360998918 cites W3024855206 @default.
- W4360998918 cites W3094061316 @default.
- W4360998918 cites W3103550568 @default.
- W4360998918 cites W3104580728 @default.
- W4360998918 cites W3199667312 @default.
- W4360998918 cites W32980360 @default.
- W4360998918 cites W4210664216 @default.
- W4360998918 cites W4235508806 @default.
- W4360998918 cites W4238101851 @default.
- W4360998918 cites W4250589301 @default.
- W4360998918 cites W4256038730 @default.
- W4360998918 cites W4294836170 @default.
- W4360998918 doi "https://doi.org/10.1145/3589505" @default.
- W4360998918 hasPublicationYear "2023" @default.
- W4360998918 type Work @default.
- W4360998918 citedByCount "0" @default.
- W4360998918 crossrefType "journal-article" @default.
- W4360998918 hasAuthorship W4360998918A5002548887 @default.
- W4360998918 hasAuthorship W4360998918A5024426907 @default.
- W4360998918 hasAuthorship W4360998918A5057880103 @default.
- W4360998918 hasAuthorship W4360998918A5080051337 @default.
- W4360998918 hasBestOaLocation W43609989181 @default.
- W4360998918 hasConcept C105795698 @default.
- W4360998918 hasConcept C110121322 @default.
- W4360998918 hasConcept C112680207 @default.
- W4360998918 hasConcept C114614502 @default.
- W4360998918 hasConcept C120665830 @default.
- W4360998918 hasConcept C121332964 @default.
- W4360998918 hasConcept C126255220 @default.
- W4360998918 hasConcept C130787639 @default.
- W4360998918 hasConcept C134306372 @default.
- W4360998918 hasConcept C134912446 @default.
- W4360998918 hasConcept C140779682 @default.
- W4360998918 hasConcept C157972887 @default.
- W4360998918 hasConcept C19499675 @default.
- W4360998918 hasConcept C2524010 @default.
- W4360998918 hasConcept C33676613 @default.
- W4360998918 hasConcept C33923547 @default.
- W4360998918 hasConcept C63553672 @default.
- W4360998918 hasConcept C77553402 @default.
- W4360998918 hasConcept C94915269 @default.
- W4360998918 hasConceptScore W4360998918C105795698 @default.
- W4360998918 hasConceptScore W4360998918C110121322 @default.
- W4360998918 hasConceptScore W4360998918C112680207 @default.
- W4360998918 hasConceptScore W4360998918C114614502 @default.
- W4360998918 hasConceptScore W4360998918C120665830 @default.
- W4360998918 hasConceptScore W4360998918C121332964 @default.
- W4360998918 hasConceptScore W4360998918C126255220 @default.
- W4360998918 hasConceptScore W4360998918C130787639 @default.