Matches in SemOpenAlex for { <https://semopenalex.org/work/W1574994635> ?p ?o ?g. }
Showing items 1 to 99 of
99
with 100 items per page.
- W1574994635 endingPage "1624" @default.
- W1574994635 startingPage "1589" @default.
- W1574994635 abstract "In this paper, we consider comparison-based adaptive stochastic algorithms for solving numerical optimization problems. We consider a specific subclass of algorithms that we call comparison-based step-size adaptive randomized search (CB-SARS), where the state variables at a given iteration are a vector of the search space and a positive parameter, the step-size, typically control's the overall standard deviation of the underlying search distribution. We investigate the linear convergence of CB-SARS on scaling-invariant objective functions. Scaling-invariant functions preserve the ordering of points w.r.t. their function value when the points are scaled with the same positive parameter (the scaling is done w.r.t. a fixed reference point). This class of functions includes norms composed with strictly increasing functions as well as many non-quasi-convex and noncontinuous functions. On scaling-invariant functions, we show the existence of a homogeneous Markov chain, as a consequence of natural invariance properties of CB-SARS (essentially scale-invariance and invariance to strictly increasing transformation of the objective function). We then derive sufficient conditions for global linear convergence of CB-SARS, expressed in terms of different stability conditions of the normalized homogeneous Markov chain (irreducibility, positivity, Harris recurrence, geometric ergodicity) and thus define a general methodology for proving global linear convergence of CB-SARS algorithms on scaling-invariant functions. As a by-product we provide a connexion between comparison-based adaptive stochastic algorithms and Markov chain Monte Carlo algorithms." @default.
- W1574994635 created "2016-06-24" @default.
- W1574994635 creator A5038156559 @default.
- W1574994635 creator A5039669927 @default.
- W1574994635 date "2016-01-01" @default.
- W1574994635 modified "2023-09-28" @default.
- W1574994635 title "Linear Convergence of Comparison-based Step-size Adaptive Randomized Search via Stability of Markov Chains" @default.
- W1574994635 cites W1576660662 @default.
- W1574994635 cites W1965748532 @default.
- W1574994635 cites W1976503157 @default.
- W1574994635 cites W1991332019 @default.
- W1574994635 cites W2014337138 @default.
- W1574994635 cites W2024372894 @default.
- W1574994635 cites W2024991751 @default.
- W1574994635 cites W2027964569 @default.
- W1574994635 cites W2043277540 @default.
- W1574994635 cites W2054875385 @default.
- W1574994635 cites W2075208118 @default.
- W1574994635 cites W2112036188 @default.
- W1574994635 cites W2155245047 @default.
- W1574994635 cites W2171074980 @default.
- W1574994635 cites W2950882985 @default.
- W1574994635 cites W2962782524 @default.
- W1574994635 cites W4251766996 @default.
- W1574994635 doi "https://doi.org/10.1137/140984038" @default.
- W1574994635 hasPublicationYear "2016" @default.
- W1574994635 type Work @default.
- W1574994635 sameAs 1574994635 @default.
- W1574994635 citedByCount "28" @default.
- W1574994635 countsByYear W15749946352014 @default.
- W1574994635 countsByYear W15749946352017 @default.
- W1574994635 countsByYear W15749946352018 @default.
- W1574994635 countsByYear W15749946352019 @default.
- W1574994635 countsByYear W15749946352020 @default.
- W1574994635 countsByYear W15749946352021 @default.
- W1574994635 countsByYear W15749946352022 @default.
- W1574994635 countsByYear W15749946352023 @default.
- W1574994635 crossrefType "journal-article" @default.
- W1574994635 hasAuthorship W1574994635A5038156559 @default.
- W1574994635 hasAuthorship W1574994635A5039669927 @default.
- W1574994635 hasBestOaLocation W15749946352 @default.
- W1574994635 hasConcept C105795698 @default.
- W1574994635 hasConcept C126255220 @default.
- W1574994635 hasConcept C127162648 @default.
- W1574994635 hasConcept C134306372 @default.
- W1574994635 hasConcept C190470478 @default.
- W1574994635 hasConcept C201779956 @default.
- W1574994635 hasConcept C2524010 @default.
- W1574994635 hasConcept C28826006 @default.
- W1574994635 hasConcept C31258907 @default.
- W1574994635 hasConcept C33923547 @default.
- W1574994635 hasConcept C37914503 @default.
- W1574994635 hasConcept C41008148 @default.
- W1574994635 hasConcept C57869625 @default.
- W1574994635 hasConcept C61445026 @default.
- W1574994635 hasConcept C98763669 @default.
- W1574994635 hasConcept C99844830 @default.
- W1574994635 hasConceptScore W1574994635C105795698 @default.
- W1574994635 hasConceptScore W1574994635C126255220 @default.
- W1574994635 hasConceptScore W1574994635C127162648 @default.
- W1574994635 hasConceptScore W1574994635C134306372 @default.
- W1574994635 hasConceptScore W1574994635C190470478 @default.
- W1574994635 hasConceptScore W1574994635C201779956 @default.
- W1574994635 hasConceptScore W1574994635C2524010 @default.
- W1574994635 hasConceptScore W1574994635C28826006 @default.
- W1574994635 hasConceptScore W1574994635C31258907 @default.
- W1574994635 hasConceptScore W1574994635C33923547 @default.
- W1574994635 hasConceptScore W1574994635C37914503 @default.
- W1574994635 hasConceptScore W1574994635C41008148 @default.
- W1574994635 hasConceptScore W1574994635C57869625 @default.
- W1574994635 hasConceptScore W1574994635C61445026 @default.
- W1574994635 hasConceptScore W1574994635C98763669 @default.
- W1574994635 hasConceptScore W1574994635C99844830 @default.
- W1574994635 hasFunder F4320320883 @default.
- W1574994635 hasIssue "3" @default.
- W1574994635 hasLocation W15749946351 @default.
- W1574994635 hasLocation W15749946352 @default.
- W1574994635 hasLocation W15749946353 @default.
- W1574994635 hasLocation W15749946354 @default.
- W1574994635 hasLocation W15749946355 @default.
- W1574994635 hasOpenAccess W1574994635 @default.
- W1574994635 hasPrimaryLocation W15749946351 @default.
- W1574994635 hasRelatedWork W1846292136 @default.
- W1574994635 hasRelatedWork W2128702080 @default.
- W1574994635 hasRelatedWork W2331575234 @default.
- W1574994635 hasRelatedWork W2950382421 @default.
- W1574994635 hasRelatedWork W2990862925 @default.
- W1574994635 hasRelatedWork W3014543271 @default.
- W1574994635 hasRelatedWork W3049141553 @default.
- W1574994635 hasRelatedWork W4236265495 @default.
- W1574994635 hasRelatedWork W4298218172 @default.
- W1574994635 hasRelatedWork W4310623407 @default.
- W1574994635 hasVolume "26" @default.
- W1574994635 isParatext "false" @default.
- W1574994635 isRetracted "false" @default.
- W1574994635 magId "1574994635" @default.
- W1574994635 workType "article" @default.