Matches in SemOpenAlex for { <https://semopenalex.org/work/W4297686275> ?p ?o ?g. }
Showing items 1 to 59 of
59
with 100 items per page.
- W4297686275 abstract "Ridge leverage scores provide a balance between low-rank approximation and regularization, and are ubiquitous in randomized linear algebra and machine learning. Deterministic algorithms are also of interest in the moderately big data regime, because deterministic algorithms provide interpretability to the practitioner by having no failure probability and always returning the same results. We provide provable guarantees for deterministic column sampling using ridge leverage scores. The matrix sketch returned by our algorithm is a column subset of the original matrix, yielding additional interpretability. Like the randomized counterparts, the deterministic algorithm provides (1 + {epsilon}) error column subset selection, (1 + {epsilon}) error projection-cost preservation, and an additive-multiplicative spectral bound. We also show that under the assumption of power-law decay of ridge leverage scores, this deterministic algorithm is provably as accurate as randomized algorithms. Lastly, ridge regression is frequently used to regularize ill-posed linear least-squares problems. While ridge regression provides shrinkage for the regression coefficients, many of the coefficients remain small but non-zero. Performing ridge regression with the matrix sketch returned by our algorithm and a particular regularization parameter forces coefficients to zero and has a provable (1 + {epsilon}) bound on the statistical risk. As such, it is an interesting alternative to elastic net regularization." @default.
- W4297686275 created "2022-09-30" @default.
- W4297686275 creator A5068492086 @default.
- W4297686275 date "2018-03-15" @default.
- W4297686275 modified "2023-09-26" @default.
- W4297686275 title "Ridge Regression and Provable Deterministic Ridge Leverage Score Sampling" @default.
- W4297686275 doi "https://doi.org/10.48550/arxiv.1803.06010" @default.
- W4297686275 hasPublicationYear "2018" @default.
- W4297686275 type Work @default.
- W4297686275 citedByCount "0" @default.
- W4297686275 crossrefType "posted-content" @default.
- W4297686275 hasAuthorship W4297686275A5068492086 @default.
- W4297686275 hasBestOaLocation W42976862751 @default.
- W4297686275 hasConcept C105795698 @default.
- W4297686275 hasConcept C11413529 @default.
- W4297686275 hasConcept C126255220 @default.
- W4297686275 hasConcept C151730666 @default.
- W4297686275 hasConcept C153083717 @default.
- W4297686275 hasConcept C154945302 @default.
- W4297686275 hasConcept C203868755 @default.
- W4297686275 hasConcept C2776135515 @default.
- W4297686275 hasConcept C2781067378 @default.
- W4297686275 hasConcept C32277403 @default.
- W4297686275 hasConcept C33923547 @default.
- W4297686275 hasConcept C41008148 @default.
- W4297686275 hasConcept C48921125 @default.
- W4297686275 hasConcept C83546350 @default.
- W4297686275 hasConcept C86803240 @default.
- W4297686275 hasConceptScore W4297686275C105795698 @default.
- W4297686275 hasConceptScore W4297686275C11413529 @default.
- W4297686275 hasConceptScore W4297686275C126255220 @default.
- W4297686275 hasConceptScore W4297686275C151730666 @default.
- W4297686275 hasConceptScore W4297686275C153083717 @default.
- W4297686275 hasConceptScore W4297686275C154945302 @default.
- W4297686275 hasConceptScore W4297686275C203868755 @default.
- W4297686275 hasConceptScore W4297686275C2776135515 @default.
- W4297686275 hasConceptScore W4297686275C2781067378 @default.
- W4297686275 hasConceptScore W4297686275C32277403 @default.
- W4297686275 hasConceptScore W4297686275C33923547 @default.
- W4297686275 hasConceptScore W4297686275C41008148 @default.
- W4297686275 hasConceptScore W4297686275C48921125 @default.
- W4297686275 hasConceptScore W4297686275C83546350 @default.
- W4297686275 hasConceptScore W4297686275C86803240 @default.
- W4297686275 hasLocation W42976862751 @default.
- W4297686275 hasOpenAccess W4297686275 @default.
- W4297686275 hasPrimaryLocation W42976862751 @default.
- W4297686275 hasRelatedWork W1579895195 @default.
- W4297686275 hasRelatedWork W1966326540 @default.
- W4297686275 hasRelatedWork W2104229089 @default.
- W4297686275 hasRelatedWork W2344853450 @default.
- W4297686275 hasRelatedWork W2404067730 @default.
- W4297686275 hasRelatedWork W2801740468 @default.
- W4297686275 hasRelatedWork W2899839525 @default.
- W4297686275 hasRelatedWork W3026087809 @default.
- W4297686275 hasRelatedWork W3042131679 @default.
- W4297686275 hasRelatedWork W3134960206 @default.
- W4297686275 isParatext "false" @default.
- W4297686275 isRetracted "false" @default.
- W4297686275 workType "article" @default.