Matches in SemOpenAlex for { <https://semopenalex.org/work/W2034446667> ?p ?o ?g. }
Showing items 1 to 99 of
99
with 100 items per page.
- W2034446667 abstract "We study the optimization of a continuous function by its stochastic relaxation, i.e., the optimization of the expected value of the function itself with respect to a density in a statistical model. We focus on gradient descent techniques applied to models from the exponential family and in particular on the multivariate Gaussian distribution. From the theory of the exponential family, we reparametrize the Gaussian distribution using natural and expectation parameters, and we derive formulas for natural gradients in both parameterizations. We discuss some advantages of the natural parameterization for the identification of sub-models in the Gaussian distribution based on conditional independence assumptions among variables. Gaussian distributions are widely used in stochastic optimization and in particular in model-based Evolutionary Computation, as in Estimation of Distribution Algorithms and Evolutionary Strategies. By studying natural gradient flows over Gaussian distributions our analysis and results directly apply to the study of CMA-ES and NES algorithms." @default.
- W2034446667 created "2016-06-24" @default.
- W2034446667 creator A5006237017 @default.
- W2034446667 creator A5074786556 @default.
- W2034446667 date "2015-01-17" @default.
- W2034446667 modified "2023-09-30" @default.
- W2034446667 title "Information Geometry of the Gaussian Distribution in View of Stochastic Optimization" @default.
- W2034446667 cites W1520168181 @default.
- W2034446667 cites W1687697105 @default.
- W2034446667 cites W1970789124 @default.
- W2034446667 cites W1980841879 @default.
- W2034446667 cites W2018595942 @default.
- W2034446667 cites W2034813183 @default.
- W2034446667 cites W2058157079 @default.
- W2034446667 cites W2060624994 @default.
- W2034446667 cites W2061414435 @default.
- W2034446667 cites W2097230740 @default.
- W2034446667 cites W2112036188 @default.
- W2034446667 cites W2116990014 @default.
- W2034446667 cites W2166160300 @default.
- W2034446667 cites W2475483989 @default.
- W2034446667 cites W3007384386 @default.
- W2034446667 cites W4205293427 @default.
- W2034446667 doi "https://doi.org/10.1145/2725494.2725510" @default.
- W2034446667 hasPublicationYear "2015" @default.
- W2034446667 type Work @default.
- W2034446667 sameAs 2034446667 @default.
- W2034446667 citedByCount "26" @default.
- W2034446667 countsByYear W20344466672015 @default.
- W2034446667 countsByYear W20344466672018 @default.
- W2034446667 countsByYear W20344466672019 @default.
- W2034446667 countsByYear W20344466672020 @default.
- W2034446667 countsByYear W20344466672021 @default.
- W2034446667 countsByYear W20344466672022 @default.
- W2034446667 countsByYear W20344466672023 @default.
- W2034446667 crossrefType "proceedings-article" @default.
- W2034446667 hasAuthorship W2034446667A5006237017 @default.
- W2034446667 hasAuthorship W2034446667A5074786556 @default.
- W2034446667 hasConcept C105795698 @default.
- W2034446667 hasConcept C121332964 @default.
- W2034446667 hasConcept C126255220 @default.
- W2034446667 hasConcept C153258448 @default.
- W2034446667 hasConcept C154945302 @default.
- W2034446667 hasConcept C161584116 @default.
- W2034446667 hasConcept C163716315 @default.
- W2034446667 hasConcept C177384507 @default.
- W2034446667 hasConcept C18912344 @default.
- W2034446667 hasConcept C194387892 @default.
- W2034446667 hasConcept C197055811 @default.
- W2034446667 hasConcept C202021718 @default.
- W2034446667 hasConcept C28826006 @default.
- W2034446667 hasConcept C33923547 @default.
- W2034446667 hasConcept C41008148 @default.
- W2034446667 hasConcept C43555835 @default.
- W2034446667 hasConcept C50644808 @default.
- W2034446667 hasConcept C51267290 @default.
- W2034446667 hasConcept C55974624 @default.
- W2034446667 hasConcept C60775368 @default.
- W2034446667 hasConcept C61326573 @default.
- W2034446667 hasConcept C62520636 @default.
- W2034446667 hasConceptScore W2034446667C105795698 @default.
- W2034446667 hasConceptScore W2034446667C121332964 @default.
- W2034446667 hasConceptScore W2034446667C126255220 @default.
- W2034446667 hasConceptScore W2034446667C153258448 @default.
- W2034446667 hasConceptScore W2034446667C154945302 @default.
- W2034446667 hasConceptScore W2034446667C161584116 @default.
- W2034446667 hasConceptScore W2034446667C163716315 @default.
- W2034446667 hasConceptScore W2034446667C177384507 @default.
- W2034446667 hasConceptScore W2034446667C18912344 @default.
- W2034446667 hasConceptScore W2034446667C194387892 @default.
- W2034446667 hasConceptScore W2034446667C197055811 @default.
- W2034446667 hasConceptScore W2034446667C202021718 @default.
- W2034446667 hasConceptScore W2034446667C28826006 @default.
- W2034446667 hasConceptScore W2034446667C33923547 @default.
- W2034446667 hasConceptScore W2034446667C41008148 @default.
- W2034446667 hasConceptScore W2034446667C43555835 @default.
- W2034446667 hasConceptScore W2034446667C50644808 @default.
- W2034446667 hasConceptScore W2034446667C51267290 @default.
- W2034446667 hasConceptScore W2034446667C55974624 @default.
- W2034446667 hasConceptScore W2034446667C60775368 @default.
- W2034446667 hasConceptScore W2034446667C61326573 @default.
- W2034446667 hasConceptScore W2034446667C62520636 @default.
- W2034446667 hasLocation W20344466671 @default.
- W2034446667 hasOpenAccess W2034446667 @default.
- W2034446667 hasPrimaryLocation W20344466671 @default.
- W2034446667 hasRelatedWork W115602763 @default.
- W2034446667 hasRelatedWork W1970063255 @default.
- W2034446667 hasRelatedWork W2008489469 @default.
- W2034446667 hasRelatedWork W2022574511 @default.
- W2034446667 hasRelatedWork W2034446667 @default.
- W2034446667 hasRelatedWork W2092366338 @default.
- W2034446667 hasRelatedWork W2150133676 @default.
- W2034446667 hasRelatedWork W2156205196 @default.
- W2034446667 hasRelatedWork W3131275255 @default.
- W2034446667 hasRelatedWork W2341897833 @default.
- W2034446667 isParatext "false" @default.
- W2034446667 isRetracted "false" @default.
- W2034446667 magId "2034446667" @default.
- W2034446667 workType "article" @default.