Matches in SemOpenAlex for { <https://semopenalex.org/work/W2994702989> ?p ?o ?g. }
Showing items 1 to 71 of
71
with 100 items per page.
- W2994702989 abstract "This thesis deals with the problem of modeling and estimation of high-dimensional MoE models, towards effective density estimation, prediction and clustering of such heterogeneous and high-dimensional data. We propose new strategies based on regularized maximum-likelihood estimation (MLE) of MoE models to overcome the limitations of standard methods, including MLE estimation with Expectation-Maximization (EM) algorithms, and to simultaneously perform feature selection so that sparse models are encouraged in such a high-dimensional setting. We first introduce a mixture-of-experts' parameter estimation and variable selection methodology, based on $ell_1$ (lasso) regularizations and the EM framework, for regression and clustering suited to high-dimensional contexts. Then, we extend the method to regularized mixture of experts models for discrete data, including classification. We develop efficient algorithms to maximize the proposed $ell_1$-penalized observed-data log-likelihood function. Our proposed strategies enjoy the efficient monotone maximization of the optimized criterion, and unlike previous approaches, they do not rely on approximations on the penalty functions, avoid matrix inversion, and exploit the efficiency of the coordinate ascent algorithm, particularly within the proximal Newton-based approach." @default.
- W2994702989 created "2019-12-26" @default.
- W2994702989 creator A5039569465 @default.
- W2994702989 date "2019-12-03" @default.
- W2994702989 modified "2023-09-24" @default.
- W2994702989 title "Estimation and feature selection in high-dimensional mixtures-of-experts models" @default.
- W2994702989 hasPublicationYear "2019" @default.
- W2994702989 type Work @default.
- W2994702989 sameAs 2994702989 @default.
- W2994702989 citedByCount "0" @default.
- W2994702989 crossrefType "dissertation" @default.
- W2994702989 hasAuthorship W2994702989A5039569465 @default.
- W2994702989 hasConcept C105795698 @default.
- W2994702989 hasConcept C11413529 @default.
- W2994702989 hasConcept C124101348 @default.
- W2994702989 hasConcept C126255220 @default.
- W2994702989 hasConcept C136764020 @default.
- W2994702989 hasConcept C148483581 @default.
- W2994702989 hasConcept C154945302 @default.
- W2994702989 hasConcept C157553263 @default.
- W2994702989 hasConcept C182081679 @default.
- W2994702989 hasConcept C184509293 @default.
- W2994702989 hasConcept C33923547 @default.
- W2994702989 hasConcept C37616216 @default.
- W2994702989 hasConcept C41008148 @default.
- W2994702989 hasConcept C49781872 @default.
- W2994702989 hasConcept C73555534 @default.
- W2994702989 hasConcept C93959086 @default.
- W2994702989 hasConceptScore W2994702989C105795698 @default.
- W2994702989 hasConceptScore W2994702989C11413529 @default.
- W2994702989 hasConceptScore W2994702989C124101348 @default.
- W2994702989 hasConceptScore W2994702989C126255220 @default.
- W2994702989 hasConceptScore W2994702989C136764020 @default.
- W2994702989 hasConceptScore W2994702989C148483581 @default.
- W2994702989 hasConceptScore W2994702989C154945302 @default.
- W2994702989 hasConceptScore W2994702989C157553263 @default.
- W2994702989 hasConceptScore W2994702989C182081679 @default.
- W2994702989 hasConceptScore W2994702989C184509293 @default.
- W2994702989 hasConceptScore W2994702989C33923547 @default.
- W2994702989 hasConceptScore W2994702989C37616216 @default.
- W2994702989 hasConceptScore W2994702989C41008148 @default.
- W2994702989 hasConceptScore W2994702989C49781872 @default.
- W2994702989 hasConceptScore W2994702989C73555534 @default.
- W2994702989 hasConceptScore W2994702989C93959086 @default.
- W2994702989 hasLocation W29947029891 @default.
- W2994702989 hasOpenAccess W2994702989 @default.
- W2994702989 hasPrimaryLocation W29947029891 @default.
- W2994702989 hasRelatedWork W1921790738 @default.
- W2994702989 hasRelatedWork W1944663892 @default.
- W2994702989 hasRelatedWork W1992587049 @default.
- W2994702989 hasRelatedWork W2015245929 @default.
- W2994702989 hasRelatedWork W2059279601 @default.
- W2994702989 hasRelatedWork W2083931841 @default.
- W2994702989 hasRelatedWork W2093323487 @default.
- W2994702989 hasRelatedWork W2114112206 @default.
- W2994702989 hasRelatedWork W2121486389 @default.
- W2994702989 hasRelatedWork W2126067639 @default.
- W2994702989 hasRelatedWork W2147452258 @default.
- W2994702989 hasRelatedWork W2157305948 @default.
- W2994702989 hasRelatedWork W2169089578 @default.
- W2994702989 hasRelatedWork W2266501468 @default.
- W2994702989 hasRelatedWork W2369523462 @default.
- W2994702989 hasRelatedWork W2394891180 @default.
- W2994702989 hasRelatedWork W2742708260 @default.
- W2994702989 hasRelatedWork W2897613601 @default.
- W2994702989 hasRelatedWork W2972757717 @default.
- W2994702989 hasRelatedWork W3210305248 @default.
- W2994702989 isParatext "false" @default.
- W2994702989 isRetracted "false" @default.
- W2994702989 magId "2994702989" @default.
- W2994702989 workType "dissertation" @default.