Matches in SemOpenAlex for { <https://semopenalex.org/work/W2897037976> ?p ?o ?g. }
Showing items 1 to 76 of
76
with 100 items per page.
- W2897037976 abstract "Author(s): Derezinski, Michal | Advisor(s): Warmuth, Manfred K | Abstract: In this thesis we study the following basic machine learning task: Given a fixed set of n input points in a d-dimensional linear regression problem, we wish to predict a hidden response value for each of the points. We can only afford to attain the responses for a small subset of the points that are then used to construct linear predictions for all points in the dataset. The performance of the predictions is evaluated by the total square loss on all responses. We show that a good approximate solution to this least squares problem can be obtained from just dimension d many responses by using a joint sampling technique called volume sampling. Moreover, the least squares solution obtained for the volume sampled subproblem is an unbiased estimator of optimal solution based on all n responses. This unbiasedness is a desirable property that is not shared by standard subset selection techniques.Motivated by these basic properties, we develop a theoretical framework for studying volume sampling, which leads to a number of new expectation formulas and statistical guarantees which are of importance not only to least squares regression but also numerical linear algebra in general. Our methods lead to several novel extensions of volume sampling, including a regularized variant, and we propose the first efficient algorithms which make this technique a practical tool in the machine learning toolbox. Finally, we provide experimental evidence which confirms our theoretical findings." @default.
- W2897037976 created "2018-10-26" @default.
- W2897037976 creator A5013422880 @default.
- W2897037976 date "2018-01-01" @default.
- W2897037976 modified "2023-09-27" @default.
- W2897037976 title "Volume sampling for linear regression" @default.
- W2897037976 hasPublicationYear "2018" @default.
- W2897037976 type Work @default.
- W2897037976 sameAs 2897037976 @default.
- W2897037976 citedByCount "2" @default.
- W2897037976 countsByYear W28970379762018 @default.
- W2897037976 crossrefType "journal-article" @default.
- W2897037976 hasAuthorship W2897037976A5013422880 @default.
- W2897037976 hasConcept C105795698 @default.
- W2897037976 hasConcept C106131492 @default.
- W2897037976 hasConcept C11413529 @default.
- W2897037976 hasConcept C114614502 @default.
- W2897037976 hasConcept C121332964 @default.
- W2897037976 hasConcept C126255220 @default.
- W2897037976 hasConcept C140779682 @default.
- W2897037976 hasConcept C177264268 @default.
- W2897037976 hasConcept C185429906 @default.
- W2897037976 hasConcept C199360897 @default.
- W2897037976 hasConcept C20556612 @default.
- W2897037976 hasConcept C31972630 @default.
- W2897037976 hasConcept C33676613 @default.
- W2897037976 hasConcept C33923547 @default.
- W2897037976 hasConcept C41008148 @default.
- W2897037976 hasConcept C48921125 @default.
- W2897037976 hasConcept C62520636 @default.
- W2897037976 hasConcept C9936470 @default.
- W2897037976 hasConceptScore W2897037976C105795698 @default.
- W2897037976 hasConceptScore W2897037976C106131492 @default.
- W2897037976 hasConceptScore W2897037976C11413529 @default.
- W2897037976 hasConceptScore W2897037976C114614502 @default.
- W2897037976 hasConceptScore W2897037976C121332964 @default.
- W2897037976 hasConceptScore W2897037976C126255220 @default.
- W2897037976 hasConceptScore W2897037976C140779682 @default.
- W2897037976 hasConceptScore W2897037976C177264268 @default.
- W2897037976 hasConceptScore W2897037976C185429906 @default.
- W2897037976 hasConceptScore W2897037976C199360897 @default.
- W2897037976 hasConceptScore W2897037976C20556612 @default.
- W2897037976 hasConceptScore W2897037976C31972630 @default.
- W2897037976 hasConceptScore W2897037976C33676613 @default.
- W2897037976 hasConceptScore W2897037976C33923547 @default.
- W2897037976 hasConceptScore W2897037976C41008148 @default.
- W2897037976 hasConceptScore W2897037976C48921125 @default.
- W2897037976 hasConceptScore W2897037976C62520636 @default.
- W2897037976 hasConceptScore W2897037976C9936470 @default.
- W2897037976 hasLocation W28970379761 @default.
- W2897037976 hasOpenAccess W2897037976 @default.
- W2897037976 hasPrimaryLocation W28970379761 @default.
- W2897037976 hasRelatedWork W2109033052 @default.
- W2897037976 hasRelatedWork W2284561687 @default.
- W2897037976 hasRelatedWork W2345596855 @default.
- W2897037976 hasRelatedWork W2489886790 @default.
- W2897037976 hasRelatedWork W2515672278 @default.
- W2897037976 hasRelatedWork W2523673233 @default.
- W2897037976 hasRelatedWork W2527716295 @default.
- W2897037976 hasRelatedWork W2536553067 @default.
- W2897037976 hasRelatedWork W2791553724 @default.
- W2897037976 hasRelatedWork W2908620745 @default.
- W2897037976 hasRelatedWork W2912371996 @default.
- W2897037976 hasRelatedWork W2935046338 @default.
- W2897037976 hasRelatedWork W2952228663 @default.
- W2897037976 hasRelatedWork W2953340873 @default.
- W2897037976 hasRelatedWork W2963614384 @default.
- W2897037976 hasRelatedWork W2964933009 @default.
- W2897037976 hasRelatedWork W2970072822 @default.
- W2897037976 hasRelatedWork W3038101987 @default.
- W2897037976 hasRelatedWork W3100353959 @default.
- W2897037976 hasRelatedWork W3141627247 @default.
- W2897037976 isParatext "false" @default.
- W2897037976 isRetracted "false" @default.
- W2897037976 magId "2897037976" @default.
- W2897037976 workType "article" @default.