Matches in SemOpenAlex for { <https://semopenalex.org/work/W1598629391> ?p ?o ?g. }
- W1598629391 endingPage "300" @default.
- W1598629391 startingPage "291" @default.
- W1598629391 abstract "We propose maximum likelihood estimation for learning Gaussian graphical models with a Gaussian (l22) prior on the parameters. This is in contrast to the commonly used Laplace (l1) prior for encouraging sparseness. We show that our optimization problem leads to a Riccati matrix equation, which has a closed form solution. We propose an efficient algorithm that performs a singular value decomposition of the training data. Our algorithm is O(NT2)-time and O(NT)-space for N variables and T samples. Our method is tailored to high-dimensional problems (N ≫ T), in which sparseness promoting methods become intractable. Furthermore, instead of obtaining a single solution for a specific regularization parameter, our algorithm finds the whole solution path. We show that the method has logarithmic sample complexity under the spiked covariance model. We also propose sparsification of the dense solution with provable performance guarantees. We provide techniques for using our learnt models, such as removing unimportant variables, computing likelihoods and conditional distributions. Finally, we show promising results in several gene expressions datasets." @default.
- W1598629391 created "2016-06-24" @default.
- W1598629391 creator A5038965118 @default.
- W1598629391 creator A5048915657 @default.
- W1598629391 date "2013-08-11" @default.
- W1598629391 modified "2023-09-27" @default.
- W1598629391 title "Inverse covariance estimation for high-dimensional data in linear time and space: spectral methods for Riccati and sparse models" @default.
- W1598629391 cites W123621906 @default.
- W1598629391 cites W1495344897 @default.
- W1598629391 cites W1706044825 @default.
- W1598629391 cites W2004915807 @default.
- W1598629391 cites W2020390700 @default.
- W1598629391 cites W2037062671 @default.
- W1598629391 cites W2039614643 @default.
- W1598629391 cites W2052386156 @default.
- W1598629391 cites W2055400003 @default.
- W1598629391 cites W2057516887 @default.
- W1598629391 cites W2081746825 @default.
- W1598629391 cites W2097581234 @default.
- W1598629391 cites W2106116051 @default.
- W1598629391 cites W2113455900 @default.
- W1598629391 cites W2116805437 @default.
- W1598629391 cites W2118163005 @default.
- W1598629391 cites W2120672356 @default.
- W1598629391 cites W2123499997 @default.
- W1598629391 cites W2132555912 @default.
- W1598629391 cites W2151128232 @default.
- W1598629391 cites W2170744156 @default.
- W1598629391 cites W2555830188 @default.
- W1598629391 cites W2962826552 @default.
- W1598629391 cites W2963364599 @default.
- W1598629391 cites W3105364218 @default.
- W1598629391 cites W197517825 @default.
- W1598629391 cites W2106802398 @default.
- W1598629391 hasPublicationYear "2013" @default.
- W1598629391 type Work @default.
- W1598629391 sameAs 1598629391 @default.
- W1598629391 citedByCount "3" @default.
- W1598629391 countsByYear W15986293912014 @default.
- W1598629391 countsByYear W15986293912016 @default.
- W1598629391 crossrefType "proceedings-article" @default.
- W1598629391 hasAuthorship W1598629391A5038965118 @default.
- W1598629391 hasAuthorship W1598629391A5048915657 @default.
- W1598629391 hasConcept C105795698 @default.
- W1598629391 hasConcept C11413529 @default.
- W1598629391 hasConcept C121332964 @default.
- W1598629391 hasConcept C126255220 @default.
- W1598629391 hasConcept C134306372 @default.
- W1598629391 hasConcept C135252773 @default.
- W1598629391 hasConcept C154945302 @default.
- W1598629391 hasConcept C163716315 @default.
- W1598629391 hasConcept C167928553 @default.
- W1598629391 hasConcept C178650346 @default.
- W1598629391 hasConcept C22789450 @default.
- W1598629391 hasConcept C2776135515 @default.
- W1598629391 hasConcept C28826006 @default.
- W1598629391 hasConcept C33923547 @default.
- W1598629391 hasConcept C39927690 @default.
- W1598629391 hasConcept C41008148 @default.
- W1598629391 hasConcept C62520636 @default.
- W1598629391 hasConcept C97937538 @default.
- W1598629391 hasConceptScore W1598629391C105795698 @default.
- W1598629391 hasConceptScore W1598629391C11413529 @default.
- W1598629391 hasConceptScore W1598629391C121332964 @default.
- W1598629391 hasConceptScore W1598629391C126255220 @default.
- W1598629391 hasConceptScore W1598629391C134306372 @default.
- W1598629391 hasConceptScore W1598629391C135252773 @default.
- W1598629391 hasConceptScore W1598629391C154945302 @default.
- W1598629391 hasConceptScore W1598629391C163716315 @default.
- W1598629391 hasConceptScore W1598629391C167928553 @default.
- W1598629391 hasConceptScore W1598629391C178650346 @default.
- W1598629391 hasConceptScore W1598629391C22789450 @default.
- W1598629391 hasConceptScore W1598629391C2776135515 @default.
- W1598629391 hasConceptScore W1598629391C28826006 @default.
- W1598629391 hasConceptScore W1598629391C33923547 @default.
- W1598629391 hasConceptScore W1598629391C39927690 @default.
- W1598629391 hasConceptScore W1598629391C41008148 @default.
- W1598629391 hasConceptScore W1598629391C62520636 @default.
- W1598629391 hasConceptScore W1598629391C97937538 @default.
- W1598629391 hasLocation W15986293911 @default.
- W1598629391 hasOpenAccess W1598629391 @default.
- W1598629391 hasPrimaryLocation W15986293911 @default.
- W1598629391 hasRelatedWork W1562941967 @default.
- W1598629391 hasRelatedWork W1565209436 @default.
- W1598629391 hasRelatedWork W2116805437 @default.
- W1598629391 hasRelatedWork W2133396774 @default.
- W1598629391 hasRelatedWork W2141261622 @default.
- W1598629391 hasRelatedWork W2142486893 @default.
- W1598629391 hasRelatedWork W2148974830 @default.
- W1598629391 hasRelatedWork W2170744156 @default.
- W1598629391 hasRelatedWork W2492755667 @default.
- W1598629391 hasRelatedWork W2530144749 @default.
- W1598629391 hasRelatedWork W2594924640 @default.
- W1598629391 hasRelatedWork W2804376578 @default.
- W1598629391 hasRelatedWork W2951198600 @default.
- W1598629391 hasRelatedWork W2951407072 @default.
- W1598629391 hasRelatedWork W2963662204 @default.
- W1598629391 hasRelatedWork W2970017308 @default.