Matches in SemOpenAlex for { <https://semopenalex.org/work/W2963758424> ?p ?o ?g. }
- W2963758424 endingPage "29" @default.
- W2963758424 startingPage "1" @default.
- W2963758424 abstract "We propose a computationally efficient random walk on a convex body which rapidly mixes and closely tracks a time-varying log-concave distribution. We develop general theoretical guarantees on the required number of steps; this number can be calculated on the fly according to the distance from and the shape of the next distribution. We then illustrate the technique on several examples. Within the context of exponential families, the proposed method produces samples from a posterior distribution which is updated as data arrive in a streaming fashion. The sampling technique can be used to track time-varying truncated distributions, as well as to obtain samples from a changing mixture model, fitted in a streaming fashion to data. In the setting of linear optimization, the proposed method has oracle complexity with best known dependence on the dimension for certain geometries. In the context of online learning and repeated games, the algorithm is an efficient method for implementing no-regret mixture forecasting strategies. Remarkably, in some of these examples, only one step of the random walk is needed to track the next distribution." @default.
- W2963758424 created "2019-07-30" @default.
- W2963758424 creator A5029536777 @default.
- W2963758424 creator A5076656836 @default.
- W2963758424 date "2017-01-01" @default.
- W2963758424 modified "2023-09-26" @default.
- W2963758424 title "EFFICIENT SAMPLING FROM TIME-VARYING LOG-CONCAVE DISTRIBUTIONS" @default.
- W2963758424 cites W1506313179 @default.
- W2963758424 cites W1508384000 @default.
- W2963758424 cites W1570963478 @default.
- W2963758424 cites W1579271636 @default.
- W2963758424 cites W1632601927 @default.
- W2963758424 cites W1964718108 @default.
- W2963758424 cites W1972309199 @default.
- W2963758424 cites W1985093013 @default.
- W2963758424 cites W1995713768 @default.
- W2963758424 cites W2011832962 @default.
- W2963758424 cites W2016384870 @default.
- W2963758424 cites W2022004112 @default.
- W2963758424 cites W2047837509 @default.
- W2963758424 cites W2063342497 @default.
- W2963758424 cites W2063986634 @default.
- W2963758424 cites W2087441176 @default.
- W2963758424 cites W2087667141 @default.
- W2963758424 cites W2093825590 @default.
- W2963758424 cites W2096772472 @default.
- W2963758424 cites W2114067803 @default.
- W2963758424 cites W2123493177 @default.
- W2963758424 cites W2124488712 @default.
- W2963758424 cites W2137307912 @default.
- W2963758424 cites W2147487384 @default.
- W2963758424 cites W2152828142 @default.
- W2963758424 cites W2159000620 @default.
- W2963758424 cites W2166076290 @default.
- W2963758424 cites W2168908795 @default.
- W2963758424 cites W2204383650 @default.
- W2963758424 cites W2611627047 @default.
- W2963758424 cites W3083047178 @default.
- W2963758424 cites W3099242408 @default.
- W2963758424 cites W3103635125 @default.
- W2963758424 cites W10518661 @default.
- W2963758424 cites W2139716865 @default.
- W2963758424 hasPublicationYear "2017" @default.
- W2963758424 type Work @default.
- W2963758424 sameAs 2963758424 @default.
- W2963758424 citedByCount "8" @default.
- W2963758424 countsByYear W29637584242016 @default.
- W2963758424 countsByYear W29637584242017 @default.
- W2963758424 countsByYear W29637584242018 @default.
- W2963758424 countsByYear W29637584242019 @default.
- W2963758424 countsByYear W29637584242020 @default.
- W2963758424 crossrefType "journal-article" @default.
- W2963758424 hasAuthorship W2963758424A5029536777 @default.
- W2963758424 hasAuthorship W2963758424A5076656836 @default.
- W2963758424 hasConcept C105795698 @default.
- W2963758424 hasConcept C106131492 @default.
- W2963758424 hasConcept C110121322 @default.
- W2963758424 hasConcept C111919701 @default.
- W2963758424 hasConcept C11413529 @default.
- W2963758424 hasConcept C114614502 @default.
- W2963758424 hasConcept C115903868 @default.
- W2963758424 hasConcept C121194460 @default.
- W2963758424 hasConcept C126255220 @default.
- W2963758424 hasConcept C134306372 @default.
- W2963758424 hasConcept C140779682 @default.
- W2963758424 hasConcept C151376022 @default.
- W2963758424 hasConcept C151730666 @default.
- W2963758424 hasConcept C185429906 @default.
- W2963758424 hasConcept C2779343474 @default.
- W2963758424 hasConcept C2781020372 @default.
- W2963758424 hasConcept C31972630 @default.
- W2963758424 hasConcept C33676613 @default.
- W2963758424 hasConcept C33923547 @default.
- W2963758424 hasConcept C41008148 @default.
- W2963758424 hasConcept C50817715 @default.
- W2963758424 hasConcept C55166926 @default.
- W2963758424 hasConcept C55350006 @default.
- W2963758424 hasConcept C73602740 @default.
- W2963758424 hasConcept C86803240 @default.
- W2963758424 hasConceptScore W2963758424C105795698 @default.
- W2963758424 hasConceptScore W2963758424C106131492 @default.
- W2963758424 hasConceptScore W2963758424C110121322 @default.
- W2963758424 hasConceptScore W2963758424C111919701 @default.
- W2963758424 hasConceptScore W2963758424C11413529 @default.
- W2963758424 hasConceptScore W2963758424C114614502 @default.
- W2963758424 hasConceptScore W2963758424C115903868 @default.
- W2963758424 hasConceptScore W2963758424C121194460 @default.
- W2963758424 hasConceptScore W2963758424C126255220 @default.
- W2963758424 hasConceptScore W2963758424C134306372 @default.
- W2963758424 hasConceptScore W2963758424C140779682 @default.
- W2963758424 hasConceptScore W2963758424C151376022 @default.
- W2963758424 hasConceptScore W2963758424C151730666 @default.
- W2963758424 hasConceptScore W2963758424C185429906 @default.
- W2963758424 hasConceptScore W2963758424C2779343474 @default.
- W2963758424 hasConceptScore W2963758424C2781020372 @default.
- W2963758424 hasConceptScore W2963758424C31972630 @default.
- W2963758424 hasConceptScore W2963758424C33676613 @default.
- W2963758424 hasConceptScore W2963758424C33923547 @default.