Matches in SemOpenAlex for { <https://semopenalex.org/work/W2595901109> ?p ?o ?g. }
- W2595901109 abstract "Feature subset selection arises in many high-dimensional applications of statistics, such as compressed sensing and genomics. The $ell_0$ penalty is ideal for this task, the caveat being it requires the NP-hard combinatorial evaluation of all models. A recent area of considerable interest is to develop efficient algorithms to fit models with a non-convex $ell_gamma$ penalty for $gammain (0,1)$, which results in sparser models than the convex $ell_1$ or lasso penalty, but is harder to fit. We propose an alternative, termed the horseshoe regularization penalty for feature subset selection, and demonstrate its theoretical and computational advantages. The distinguishing feature from existing non-convex optimization approaches is a full probabilistic representation of the penalty as the negative of the logarithm of a suitable prior, which in turn enables efficient expectation-maximization and local linear approximation algorithms for optimization and MCMC for uncertainty quantification. In synthetic and real data, the resulting algorithms provide better statistical performance, and the computation requires a fraction of time of state-of-the-art non-convex solvers." @default.
- W2595901109 created "2017-03-23" @default.
- W2595901109 creator A5032033428 @default.
- W2595901109 creator A5042890818 @default.
- W2595901109 creator A5081284665 @default.
- W2595901109 creator A5086643947 @default.
- W2595901109 date "2017-02-23" @default.
- W2595901109 modified "2023-09-27" @default.
- W2595901109 title "Horseshoe Regularization for Feature Subset Selection" @default.
- W2595901109 cites W1510659740 @default.
- W2595901109 cites W1536497620 @default.
- W2595901109 cites W1540935623 @default.
- W2595901109 cites W1827621890 @default.
- W2595901109 cites W1965169081 @default.
- W2595901109 cites W1966701961 @default.
- W2595901109 cites W1967639437 @default.
- W2595901109 cites W1989609065 @default.
- W2595901109 cites W2004810039 @default.
- W2595901109 cites W2020925091 @default.
- W2595901109 cites W2024060531 @default.
- W2595901109 cites W2026357499 @default.
- W2595901109 cites W2028781966 @default.
- W2595901109 cites W2049633694 @default.
- W2595901109 cites W2063978378 @default.
- W2595901109 cites W2074682976 @default.
- W2595901109 cites W2109363337 @default.
- W2595901109 cites W2114169935 @default.
- W2595901109 cites W2120062331 @default.
- W2595901109 cites W2122825543 @default.
- W2595901109 cites W2135046866 @default.
- W2595901109 cites W2150149003 @default.
- W2595901109 cites W2150847344 @default.
- W2595901109 cites W2152977846 @default.
- W2595901109 cites W2157801062 @default.
- W2595901109 cites W2296319761 @default.
- W2595901109 cites W2314640094 @default.
- W2595901109 cites W2343184161 @default.
- W2595901109 cites W2913535645 @default.
- W2595901109 cites W2952132522 @default.
- W2595901109 cites W2962943048 @default.
- W2595901109 cites W2963260978 @default.
- W2595901109 cites W3098707346 @default.
- W2595901109 cites W3098952422 @default.
- W2595901109 cites W3106385100 @default.
- W2595901109 cites W3126085589 @default.
- W2595901109 hasPublicationYear "2017" @default.
- W2595901109 type Work @default.
- W2595901109 sameAs 2595901109 @default.
- W2595901109 citedByCount "4" @default.
- W2595901109 countsByYear W25959011092017 @default.
- W2595901109 countsByYear W25959011092019 @default.
- W2595901109 crossrefType "posted-content" @default.
- W2595901109 hasAuthorship W2595901109A5032033428 @default.
- W2595901109 hasAuthorship W2595901109A5042890818 @default.
- W2595901109 hasAuthorship W2595901109A5081284665 @default.
- W2595901109 hasAuthorship W2595901109A5086643947 @default.
- W2595901109 hasConcept C112680207 @default.
- W2595901109 hasConcept C11413529 @default.
- W2595901109 hasConcept C126255220 @default.
- W2595901109 hasConcept C134306372 @default.
- W2595901109 hasConcept C136764020 @default.
- W2595901109 hasConcept C138885662 @default.
- W2595901109 hasConcept C148483581 @default.
- W2595901109 hasConcept C154945302 @default.
- W2595901109 hasConcept C157972887 @default.
- W2595901109 hasConcept C2524010 @default.
- W2595901109 hasConcept C2776135515 @default.
- W2595901109 hasConcept C2776330181 @default.
- W2595901109 hasConcept C2776401178 @default.
- W2595901109 hasConcept C33923547 @default.
- W2595901109 hasConcept C37616216 @default.
- W2595901109 hasConcept C39927690 @default.
- W2595901109 hasConcept C41008148 @default.
- W2595901109 hasConcept C41895202 @default.
- W2595901109 hasConcept C45374587 @default.
- W2595901109 hasConcept C49937458 @default.
- W2595901109 hasConceptScore W2595901109C112680207 @default.
- W2595901109 hasConceptScore W2595901109C11413529 @default.
- W2595901109 hasConceptScore W2595901109C126255220 @default.
- W2595901109 hasConceptScore W2595901109C134306372 @default.
- W2595901109 hasConceptScore W2595901109C136764020 @default.
- W2595901109 hasConceptScore W2595901109C138885662 @default.
- W2595901109 hasConceptScore W2595901109C148483581 @default.
- W2595901109 hasConceptScore W2595901109C154945302 @default.
- W2595901109 hasConceptScore W2595901109C157972887 @default.
- W2595901109 hasConceptScore W2595901109C2524010 @default.
- W2595901109 hasConceptScore W2595901109C2776135515 @default.
- W2595901109 hasConceptScore W2595901109C2776330181 @default.
- W2595901109 hasConceptScore W2595901109C2776401178 @default.
- W2595901109 hasConceptScore W2595901109C33923547 @default.
- W2595901109 hasConceptScore W2595901109C37616216 @default.
- W2595901109 hasConceptScore W2595901109C39927690 @default.
- W2595901109 hasConceptScore W2595901109C41008148 @default.
- W2595901109 hasConceptScore W2595901109C41895202 @default.
- W2595901109 hasConceptScore W2595901109C45374587 @default.
- W2595901109 hasConceptScore W2595901109C49937458 @default.
- W2595901109 hasLocation W25959011091 @default.
- W2595901109 hasOpenAccess W2595901109 @default.
- W2595901109 hasPrimaryLocation W25959011091 @default.
- W2595901109 hasRelatedWork W105745955 @default.