Matches in SemOpenAlex for { <https://semopenalex.org/work/W2983004766> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W2983004766 abstract "Regularized least-squares (kernel-ridge / Gaussian process) regression is a fundamental algorithm of statistics and machine learning. Because generic algorithms for the exact solution have cubic complexity in the number of datapoints, large datasets require to resort to approximations. In this work, the computation of the least-squares prediction is itself treated as a probabilistic inference problem. We propose a structured Gaussian regression model on the kernel function that uses projections of the kernel matrix to obtain a low-rank approximation of the kernel and the matrix. A central result is an enhanced way to use the method of conjugate gradients for the specific setting of least-squares regression as encountered in machine learning. Our method improves the approximation of the kernel ridge regressor / Gaussian process posterior mean over vanilla conjugate gradients and, allows computation of the posterior variance and the log marginal likelihood (evidence) without further overhead." @default.
- W2983004766 created "2019-11-22" @default.
- W2983004766 creator A5022872779 @default.
- W2983004766 creator A5086283956 @default.
- W2983004766 date "2019-11-14" @default.
- W2983004766 modified "2023-09-23" @default.
- W2983004766 title "Conjugate Gradients for Kernel Machines" @default.
- W2983004766 cites W2127650263 @default.
- W2983004766 cites W2129564505 @default.
- W2983004766 cites W2150582689 @default.
- W2983004766 cites W2751238863 @default.
- W2983004766 hasPublicationYear "2019" @default.
- W2983004766 type Work @default.
- W2983004766 sameAs 2983004766 @default.
- W2983004766 citedByCount "0" @default.
- W2983004766 crossrefType "posted-content" @default.
- W2983004766 hasAuthorship W2983004766A5022872779 @default.
- W2983004766 hasAuthorship W2983004766A5086283956 @default.
- W2983004766 hasConcept C105795698 @default.
- W2983004766 hasConcept C107673813 @default.
- W2983004766 hasConcept C11413529 @default.
- W2983004766 hasConcept C114614502 @default.
- W2983004766 hasConcept C121332964 @default.
- W2983004766 hasConcept C122280245 @default.
- W2983004766 hasConcept C12267149 @default.
- W2983004766 hasConcept C126255220 @default.
- W2983004766 hasConcept C134517425 @default.
- W2983004766 hasConcept C154945302 @default.
- W2983004766 hasConcept C163716315 @default.
- W2983004766 hasConcept C182335926 @default.
- W2983004766 hasConcept C195699287 @default.
- W2983004766 hasConcept C26004113 @default.
- W2983004766 hasConcept C28826006 @default.
- W2983004766 hasConcept C33923547 @default.
- W2983004766 hasConcept C41008148 @default.
- W2983004766 hasConcept C45374587 @default.
- W2983004766 hasConcept C57830394 @default.
- W2983004766 hasConcept C61326573 @default.
- W2983004766 hasConcept C62520636 @default.
- W2983004766 hasConcept C74193536 @default.
- W2983004766 hasConceptScore W2983004766C105795698 @default.
- W2983004766 hasConceptScore W2983004766C107673813 @default.
- W2983004766 hasConceptScore W2983004766C11413529 @default.
- W2983004766 hasConceptScore W2983004766C114614502 @default.
- W2983004766 hasConceptScore W2983004766C121332964 @default.
- W2983004766 hasConceptScore W2983004766C122280245 @default.
- W2983004766 hasConceptScore W2983004766C12267149 @default.
- W2983004766 hasConceptScore W2983004766C126255220 @default.
- W2983004766 hasConceptScore W2983004766C134517425 @default.
- W2983004766 hasConceptScore W2983004766C154945302 @default.
- W2983004766 hasConceptScore W2983004766C163716315 @default.
- W2983004766 hasConceptScore W2983004766C182335926 @default.
- W2983004766 hasConceptScore W2983004766C195699287 @default.
- W2983004766 hasConceptScore W2983004766C26004113 @default.
- W2983004766 hasConceptScore W2983004766C28826006 @default.
- W2983004766 hasConceptScore W2983004766C33923547 @default.
- W2983004766 hasConceptScore W2983004766C41008148 @default.
- W2983004766 hasConceptScore W2983004766C45374587 @default.
- W2983004766 hasConceptScore W2983004766C57830394 @default.
- W2983004766 hasConceptScore W2983004766C61326573 @default.
- W2983004766 hasConceptScore W2983004766C62520636 @default.
- W2983004766 hasConceptScore W2983004766C74193536 @default.
- W2983004766 hasOpenAccess W2983004766 @default.
- W2983004766 hasRelatedWork W166221275 @default.
- W2983004766 hasRelatedWork W1969250928 @default.
- W2983004766 hasRelatedWork W2021607192 @default.
- W2983004766 hasRelatedWork W2072037102 @default.
- W2983004766 hasRelatedWork W2106353342 @default.
- W2983004766 hasRelatedWork W2108250929 @default.
- W2983004766 hasRelatedWork W2155030296 @default.
- W2983004766 hasRelatedWork W2169522260 @default.
- W2983004766 hasRelatedWork W2261298172 @default.
- W2983004766 hasRelatedWork W2353293908 @default.
- W2983004766 hasRelatedWork W2752674399 @default.
- W2983004766 hasRelatedWork W2794048703 @default.
- W2983004766 hasRelatedWork W2921157110 @default.
- W2983004766 hasRelatedWork W2964181129 @default.
- W2983004766 hasRelatedWork W3006767791 @default.
- W2983004766 hasRelatedWork W3011968734 @default.
- W2983004766 hasRelatedWork W3026219810 @default.
- W2983004766 hasRelatedWork W581536292 @default.
- W2983004766 hasRelatedWork W765416423 @default.
- W2983004766 hasRelatedWork W2008369364 @default.
- W2983004766 isParatext "false" @default.
- W2983004766 isRetracted "false" @default.
- W2983004766 magId "2983004766" @default.
- W2983004766 workType "article" @default.