Matches in SemOpenAlex for { <https://semopenalex.org/work/W2734851461> ?p ?o ?g. }
Showing items 1 to 69 of
69
with 100 items per page.
- W2734851461 endingPage "44" @default.
- W2734851461 startingPage "1" @default.
- W2734851461 abstract "Convergence rate results are derived for a stochastic optimization problem where a performance measure is minimized with respect to a vector parameter t. Assuming that a gradient estimator is available and that both the bias and the variance of the estimator are (known) functions of the budget devoted to its computation, the gradient estimator is employed in conjunction with a stochastic approximation (SA) algorithm. Our interest is to figure out how to allocate the total available computational budget to the successive SA iterations. The effort is devoted to solving the asymptotic version of this problem by finding the convergence rate of SA toward the optimizer, first as a function of the number of iterations and then as a function of the total computational effort. As a result the optimal rate of increase of the computational budget per iteration can be found. Explicit expressions for the case where the computational budget devoted to an iteration is a polynomial in the iteration number, and where the bias and variance of the gradient estimator are polynomials of the computational budget, are derived. Applications include the optimization of steady-state simulation models with likelihood ratio, perturbation analysis, or finite-difference gradient estimators; optimization of infinite-horizon models with discounting; optimization of functions of several expectations; and so on. Several examples are discussed. Our results readily generalize to general root-finding problems." @default.
- W2734851461 created "2017-07-21" @default.
- W2734851461 creator A5008853967 @default.
- W2734851461 creator A5091510633 @default.
- W2734851461 date "1995-02-01" @default.
- W2734851461 modified "2023-10-15" @default.
- W2734851461 title "Budget-Dependent Convergence Rate of Stochastic Approximation" @default.
- W2734851461 hasPublicationYear "1995" @default.
- W2734851461 type Work @default.
- W2734851461 sameAs 2734851461 @default.
- W2734851461 citedByCount "1" @default.
- W2734851461 crossrefType "journal-article" @default.
- W2734851461 hasAuthorship W2734851461A5008853967 @default.
- W2734851461 hasAuthorship W2734851461A5091510633 @default.
- W2734851461 hasConcept C105795698 @default.
- W2734851461 hasConcept C126255220 @default.
- W2734851461 hasConcept C137836250 @default.
- W2734851461 hasConcept C162324750 @default.
- W2734851461 hasConcept C185429906 @default.
- W2734851461 hasConcept C26517878 @default.
- W2734851461 hasConcept C2777303404 @default.
- W2734851461 hasConcept C28826006 @default.
- W2734851461 hasConcept C33923547 @default.
- W2734851461 hasConcept C38652104 @default.
- W2734851461 hasConcept C41008148 @default.
- W2734851461 hasConcept C50522688 @default.
- W2734851461 hasConcept C57869625 @default.
- W2734851461 hasConceptScore W2734851461C105795698 @default.
- W2734851461 hasConceptScore W2734851461C126255220 @default.
- W2734851461 hasConceptScore W2734851461C137836250 @default.
- W2734851461 hasConceptScore W2734851461C162324750 @default.
- W2734851461 hasConceptScore W2734851461C185429906 @default.
- W2734851461 hasConceptScore W2734851461C26517878 @default.
- W2734851461 hasConceptScore W2734851461C2777303404 @default.
- W2734851461 hasConceptScore W2734851461C28826006 @default.
- W2734851461 hasConceptScore W2734851461C33923547 @default.
- W2734851461 hasConceptScore W2734851461C38652104 @default.
- W2734851461 hasConceptScore W2734851461C41008148 @default.
- W2734851461 hasConceptScore W2734851461C50522688 @default.
- W2734851461 hasConceptScore W2734851461C57869625 @default.
- W2734851461 hasLocation W27348514611 @default.
- W2734851461 hasOpenAccess W2734851461 @default.
- W2734851461 hasPrimaryLocation W27348514611 @default.
- W2734851461 hasRelatedWork W1708022953 @default.
- W2734851461 hasRelatedWork W1730555343 @default.
- W2734851461 hasRelatedWork W1987308858 @default.
- W2734851461 hasRelatedWork W2029953629 @default.
- W2734851461 hasRelatedWork W2056898617 @default.
- W2734851461 hasRelatedWork W2063513670 @default.
- W2734851461 hasRelatedWork W2075181955 @default.
- W2734851461 hasRelatedWork W2120350480 @default.
- W2734851461 hasRelatedWork W2156779765 @default.
- W2734851461 hasRelatedWork W2159930037 @default.
- W2734851461 hasRelatedWork W2292776404 @default.
- W2734851461 hasRelatedWork W2621374146 @default.
- W2734851461 hasRelatedWork W2783506385 @default.
- W2734851461 hasRelatedWork W2914274927 @default.
- W2734851461 hasRelatedWork W2950025208 @default.
- W2734851461 hasRelatedWork W2963393268 @default.
- W2734851461 hasRelatedWork W3005367541 @default.
- W2734851461 hasRelatedWork W3206369166 @default.
- W2734851461 hasRelatedWork W70098597 @default.
- W2734851461 hasRelatedWork W2963132105 @default.
- W2734851461 isParatext "false" @default.
- W2734851461 isRetracted "false" @default.
- W2734851461 magId "2734851461" @default.
- W2734851461 workType "article" @default.