Matches in SemOpenAlex for { <https://semopenalex.org/work/W4236026600> ?p ?o ?g. }
Showing items 1 to 63 of
63
with 100 items per page.
- W4236026600 abstract "We extend the l <sub xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>0</sub> -norm ldquosubspectralrdquo algorithms developed for sparse-LDA (Moghaddam, 2006) and sparse-PCA (Moghaddam, 2006) to more general quadratic costs such as MSE in linear (or kernel) regression. The resulting ldquosparse least squaresrdquo (SLS) problem is also NP-hard, by way of its equivalence to a rank-1 sparse eigenvalue problem. Specifically, for minimizing general quadratic cost functions we use a highly-efficient method for direct eigenvalue computation based on partitioned matrix inverse techniques that leads to times10 <sup xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>3</sup> speed-ups over standard eigenvalue decomposition. This increased efficiency mitigates the O(n <sup xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>4</sup> ) complexity that limited the previous algorithmspsila utility for high-dimensional problems. Moreover, the new computation prioritizes the role of the less-myopic backward elimination stage which becomes even more efficient than forward selection. Similarly, branch-and-bound search for exact sparse least squares (ESLS) also benefits from partitioned matrix techniques. Our greedy sparse least squares (GSLS) algorithm generalizes Natarajanpsilas algorithm (Natarajan, 1995) also known as order-recursive matching pursuit (ORMP). Specifically, the forward pass of GSLS is exactly equivalent to ORMP but is more efficient, and by including the backward pass, which only doubles the computation, we can achieve a lower MSE than ORMP. In experimental comparisons with LARS (Efron, 2004), forward-GSLS is shown to be not only more efficient and accurate but more flexible in terms of choice of regularization." @default.
- W4236026600 created "2022-05-12" @default.
- W4236026600 creator A5068635313 @default.
- W4236026600 creator A5079364492 @default.
- W4236026600 creator A5083027866 @default.
- W4236026600 creator A5086655294 @default.
- W4236026600 date "2008-01-01" @default.
- W4236026600 modified "2023-10-02" @default.
- W4236026600 title "Sparse regression as a sparse eigenvalue problem" @default.
- W4236026600 doi "https://doi.org/10.1109/ita.2008.4601051" @default.
- W4236026600 hasPublicationYear "2008" @default.
- W4236026600 type Work @default.
- W4236026600 citedByCount "2" @default.
- W4236026600 countsByYear W42360266002012 @default.
- W4236026600 crossrefType "proceedings-article" @default.
- W4236026600 hasAuthorship W4236026600A5068635313 @default.
- W4236026600 hasAuthorship W4236026600A5079364492 @default.
- W4236026600 hasAuthorship W4236026600A5083027866 @default.
- W4236026600 hasAuthorship W4236026600A5086655294 @default.
- W4236026600 hasConcept C11413529 @default.
- W4236026600 hasConcept C114614502 @default.
- W4236026600 hasConcept C121332964 @default.
- W4236026600 hasConcept C126255220 @default.
- W4236026600 hasConcept C129844170 @default.
- W4236026600 hasConcept C158693339 @default.
- W4236026600 hasConcept C169756996 @default.
- W4236026600 hasConcept C188060507 @default.
- W4236026600 hasConcept C2524010 @default.
- W4236026600 hasConcept C28826006 @default.
- W4236026600 hasConcept C33923547 @default.
- W4236026600 hasConcept C41008148 @default.
- W4236026600 hasConcept C45374587 @default.
- W4236026600 hasConcept C62520636 @default.
- W4236026600 hasConceptScore W4236026600C11413529 @default.
- W4236026600 hasConceptScore W4236026600C114614502 @default.
- W4236026600 hasConceptScore W4236026600C121332964 @default.
- W4236026600 hasConceptScore W4236026600C126255220 @default.
- W4236026600 hasConceptScore W4236026600C129844170 @default.
- W4236026600 hasConceptScore W4236026600C158693339 @default.
- W4236026600 hasConceptScore W4236026600C169756996 @default.
- W4236026600 hasConceptScore W4236026600C188060507 @default.
- W4236026600 hasConceptScore W4236026600C2524010 @default.
- W4236026600 hasConceptScore W4236026600C28826006 @default.
- W4236026600 hasConceptScore W4236026600C33923547 @default.
- W4236026600 hasConceptScore W4236026600C41008148 @default.
- W4236026600 hasConceptScore W4236026600C45374587 @default.
- W4236026600 hasConceptScore W4236026600C62520636 @default.
- W4236026600 hasLocation W42360266001 @default.
- W4236026600 hasOpenAccess W4236026600 @default.
- W4236026600 hasPrimaryLocation W42360266001 @default.
- W4236026600 hasRelatedWork W1731257546 @default.
- W4236026600 hasRelatedWork W1988099423 @default.
- W4236026600 hasRelatedWork W1994468456 @default.
- W4236026600 hasRelatedWork W2016834887 @default.
- W4236026600 hasRelatedWork W2084328661 @default.
- W4236026600 hasRelatedWork W2099169296 @default.
- W4236026600 hasRelatedWork W2134586925 @default.
- W4236026600 hasRelatedWork W2950052959 @default.
- W4236026600 hasRelatedWork W2953378572 @default.
- W4236026600 hasRelatedWork W4292512682 @default.
- W4236026600 isParatext "false" @default.
- W4236026600 isRetracted "false" @default.
- W4236026600 workType "article" @default.