FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4324100080> ?p ?o ?g. }

• W4324100080 endingPage "538" @default.
• W4324100080 startingPage "515" @default.
• W4324100080 abstract "Importance sampling (IS) is valuable in reducing the variance of Monte Carlo sampling for many areas, including finance, rare event simulation, and Bayesian inference. It is natural and obvious to combine quasi-Monte Carlo (QMC) methods with IS to achieve a faster rate of convergence. However, a naive replacement of Monte Carlo with QMC may not work well. This paper investigates the convergence rates of randomized QMC-based IS for estimating integrals with respect to a Gaussian measure, in which the IS measure is a Gaussian or distribution. We prove that if the target function satisfies the so-called boundary growth condition and the covariance matrix of the IS density has eigenvalues no smaller than 1, then randomized QMC with the Gaussian proposal has a root mean squared error of for arbitrarily small . Similar results with a distribution as the proposal are also established. These sufficient conditions help to assess the effectiveness of IS in QMC. For some particular applications, we find that the Laplace IS, a very general approach to approximate the target function by a quadratic Taylor approximation around its mode, has eigenvalues smaller than 1, making the resulting integrand less favorable for QMC. From this point of view, when using Gaussian distributions as the IS proposal, a change of measure via Laplace IS may transform a favorable integrand into an unfavorable one for QMC although the variance of Monte Carlo sampling is reduced. We also study the effect of positivization tricks on the error rate when the integrand has mixed sign. If the smooth positivization proposed by Owen and Zhou (J. Amer. Statist. Assoc., 95 (2000), pp. 135–143) is used, the rate is retained. This is not the case if taking the positive and negative parts of the integrand. We also give some examples to verify our propositions and warn against naive replacement of Monte Carlo with QMC under IS proposals. Numerical results suggest that using Laplace IS with distributions is more robust than that with Gaussian distributions." @default.
• W4324100080 created "2023-03-14" @default.
• W4324100080 creator A5033309103 @default.
• W4324100080 creator A5037655503 @default.
• W4324100080 creator A5058665232 @default.
• W4324100080 date "2023-03-10" @default.
• W4324100080 modified "2023-09-25" @default.
• W4324100080 title "On the Error Rate of Importance Sampling with Randomized Quasi-Monte Carlo" @default.
• W4324100080 cites W1533955387 @default.
• W4324100080 cites W1572757349 @default.
• W4324100080 cites W1862031973 @default.
• W4324100080 cites W1965440168 @default.
• W4324100080 cites W1973738368 @default.
• W4324100080 cites W1981512668 @default.
• W4324100080 cites W1998105223 @default.
• W4324100080 cites W2006722592 @default.
• W4324100080 cites W2023711160 @default.
• W4324100080 cites W2024626809 @default.
• W4324100080 cites W2090692107 @default.
• W4324100080 cites W2097511294 @default.
• W4324100080 cites W2124189866 @default.
• W4324100080 cites W2124763785 @default.
• W4324100080 cites W2146299225 @default.
• W4324100080 cites W2151084831 @default.
• W4324100080 cites W2153750152 @default.
• W4324100080 cites W2228579993 @default.
• W4324100080 cites W2527484249 @default.
• W4324100080 cites W2751681773 @default.
• W4324100080 cites W2962757710 @default.
• W4324100080 cites W2963880462 @default.
• W4324100080 cites W2964193315 @default.
• W4324100080 cites W3043749415 @default.
• W4324100080 cites W3120073684 @default.
• W4324100080 cites W3125876763 @default.
• W4324100080 cites W34142743 @default.
• W4324100080 cites W39759813 @default.
• W4324100080 cites W4300580367 @default.
• W4324100080 cites W598051755 @default.
• W4324100080 doi "https://doi.org/10.1137/22m1510121" @default.
• W4324100080 hasPublicationYear "2023" @default.
• W4324100080 type Work @default.
• W4324100080 citedByCount "0" @default.
• W4324100080 crossrefType "journal-article" @default.
• W4324100080 hasAuthorship W4324100080A5033309103 @default.
• W4324100080 hasAuthorship W4324100080A5037655503 @default.
• W4324100080 hasAuthorship W4324100080A5058665232 @default.
• W4324100080 hasBestOaLocation W43241000802 @default.
• W4324100080 hasConcept C105795698 @default.
• W4324100080 hasConcept C111350023 @default.
• W4324100080 hasConcept C121332964 @default.
• W4324100080 hasConcept C127162648 @default.
• W4324100080 hasConcept C13153151 @default.
• W4324100080 hasConcept C132725507 @default.
• W4324100080 hasConcept C163716315 @default.
• W4324100080 hasConcept C178650346 @default.
• W4324100080 hasConcept C19499675 @default.
• W4324100080 hasConcept C28826006 @default.
• W4324100080 hasConcept C31258907 @default.
• W4324100080 hasConcept C33923547 @default.
• W4324100080 hasConcept C41008148 @default.
• W4324100080 hasConcept C52740198 @default.
• W4324100080 hasConcept C57869625 @default.
• W4324100080 hasConcept C62520636 @default.
• W4324100080 hasConcept C63320529 @default.
• W4324100080 hasConceptScore W4324100080C105795698 @default.
• W4324100080 hasConceptScore W4324100080C111350023 @default.
• W4324100080 hasConceptScore W4324100080C121332964 @default.
• W4324100080 hasConceptScore W4324100080C127162648 @default.
• W4324100080 hasConceptScore W4324100080C13153151 @default.
• W4324100080 hasConceptScore W4324100080C132725507 @default.
• W4324100080 hasConceptScore W4324100080C163716315 @default.
• W4324100080 hasConceptScore W4324100080C178650346 @default.
• W4324100080 hasConceptScore W4324100080C19499675 @default.
• W4324100080 hasConceptScore W4324100080C28826006 @default.
• W4324100080 hasConceptScore W4324100080C31258907 @default.
• W4324100080 hasConceptScore W4324100080C33923547 @default.
• W4324100080 hasConceptScore W4324100080C41008148 @default.
• W4324100080 hasConceptScore W4324100080C52740198 @default.
• W4324100080 hasConceptScore W4324100080C57869625 @default.
• W4324100080 hasConceptScore W4324100080C62520636 @default.
• W4324100080 hasConceptScore W4324100080C63320529 @default.
• W4324100080 hasFunder F4320321001 @default.
• W4324100080 hasFunder F4320334898 @default.
• W4324100080 hasFunder F4320337111 @default.
• W4324100080 hasIssue "2" @default.
• W4324100080 hasLocation W43241000801 @default.
• W4324100080 hasLocation W43241000802 @default.
• W4324100080 hasOpenAccess W4324100080 @default.
• W4324100080 hasPrimaryLocation W43241000801 @default.
• W4324100080 hasRelatedWork W1996537871 @default.
• W4324100080 hasRelatedWork W2077096961 @default.
• W4324100080 hasRelatedWork W2081255987 @default.
• W4324100080 hasRelatedWork W2105032794 @default.
• W4324100080 hasRelatedWork W2129944235 @default.
• W4324100080 hasRelatedWork W2153934880 @default.
• W4324100080 hasRelatedWork W2613439504 @default.
• W4324100080 hasRelatedWork W2621502307 @default.
• W4324100080 hasRelatedWork W590971457 @default.

• next