Matches in SemOpenAlex for { <https://semopenalex.org/work/W2804128720> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W2804128720 abstract "Kernel methods represent one of the most powerful tools in machine learning to tackle problems expressed in terms of function values and derivatives. While these methods show good versatility, they are computationally intensive and have poor scalability to large data as they require operations on Gram matrices. In order to mitigate this serious computational limitation, recently randomized methods have been proposed in the literature, which allow the application of fast linear algorithms. Random Fourier features (RFF) are among the most popular and widely applied constructions: they provide an easily computable, low-dimensional feature representation for shift-invariant kernels. Despite the popularity of RFFs, very little is understood theoretically about their approximation quality. In this talk, I am going to present the main ideas and results of a detailed finite-sample theoretical analysis about the approximation quality of RFFs by (i) establishing optimal (in terms of the RFF dimension, and growing set size) performance guarantees in uniform norm, and (ii) providing guarantees in Lr (1≤r <∞) norms. I will also propose an RFF approximation to derivatives of a kernel with a theoretical study on its approximation quality." @default.
- W2804128720 created "2018-06-01" @default.
- W2804128720 creator A5023198874 @default.
- W2804128720 creator A5044512769 @default.
- W2804128720 date "2015-11-24" @default.
- W2804128720 modified "2023-10-18" @default.
- W2804128720 title "Optimal Rates for Random Fourier Feature Approximations" @default.
- W2804128720 hasPublicationYear "2015" @default.
- W2804128720 type Work @default.
- W2804128720 sameAs 2804128720 @default.
- W2804128720 citedByCount "0" @default.
- W2804128720 crossrefType "journal-article" @default.
- W2804128720 hasAuthorship W2804128720A5023198874 @default.
- W2804128720 hasAuthorship W2804128720A5044512769 @default.
- W2804128720 hasConcept C102519508 @default.
- W2804128720 hasConcept C11413529 @default.
- W2804128720 hasConcept C118615104 @default.
- W2804128720 hasConcept C126255220 @default.
- W2804128720 hasConcept C134306372 @default.
- W2804128720 hasConcept C154945302 @default.
- W2804128720 hasConcept C17744445 @default.
- W2804128720 hasConcept C190470478 @default.
- W2804128720 hasConcept C199539241 @default.
- W2804128720 hasConcept C2776359362 @default.
- W2804128720 hasConcept C28826006 @default.
- W2804128720 hasConcept C33923547 @default.
- W2804128720 hasConcept C37914503 @default.
- W2804128720 hasConcept C41008148 @default.
- W2804128720 hasConcept C48044578 @default.
- W2804128720 hasConcept C50644808 @default.
- W2804128720 hasConcept C74193536 @default.
- W2804128720 hasConcept C77088390 @default.
- W2804128720 hasConcept C91873725 @default.
- W2804128720 hasConcept C94625758 @default.
- W2804128720 hasConceptScore W2804128720C102519508 @default.
- W2804128720 hasConceptScore W2804128720C11413529 @default.
- W2804128720 hasConceptScore W2804128720C118615104 @default.
- W2804128720 hasConceptScore W2804128720C126255220 @default.
- W2804128720 hasConceptScore W2804128720C134306372 @default.
- W2804128720 hasConceptScore W2804128720C154945302 @default.
- W2804128720 hasConceptScore W2804128720C17744445 @default.
- W2804128720 hasConceptScore W2804128720C190470478 @default.
- W2804128720 hasConceptScore W2804128720C199539241 @default.
- W2804128720 hasConceptScore W2804128720C2776359362 @default.
- W2804128720 hasConceptScore W2804128720C28826006 @default.
- W2804128720 hasConceptScore W2804128720C33923547 @default.
- W2804128720 hasConceptScore W2804128720C37914503 @default.
- W2804128720 hasConceptScore W2804128720C41008148 @default.
- W2804128720 hasConceptScore W2804128720C48044578 @default.
- W2804128720 hasConceptScore W2804128720C50644808 @default.
- W2804128720 hasConceptScore W2804128720C74193536 @default.
- W2804128720 hasConceptScore W2804128720C77088390 @default.
- W2804128720 hasConceptScore W2804128720C91873725 @default.
- W2804128720 hasConceptScore W2804128720C94625758 @default.
- W2804128720 hasLocation W28041287201 @default.
- W2804128720 hasOpenAccess W2804128720 @default.
- W2804128720 hasPrimaryLocation W28041287201 @default.
- W2804128720 hasRelatedWork W1572734561 @default.
- W2804128720 hasRelatedWork W2080020343 @default.
- W2804128720 hasRelatedWork W2128307932 @default.
- W2804128720 hasRelatedWork W2139235151 @default.
- W2804128720 hasRelatedWork W2142930432 @default.
- W2804128720 hasRelatedWork W2338267636 @default.
- W2804128720 hasRelatedWork W2408554850 @default.
- W2804128720 hasRelatedWork W2786810233 @default.
- W2804128720 hasRelatedWork W2885554660 @default.
- W2804128720 hasRelatedWork W2886452169 @default.
- W2804128720 hasRelatedWork W2886921478 @default.
- W2804128720 hasRelatedWork W2963075548 @default.
- W2804128720 hasRelatedWork W2963980562 @default.
- W2804128720 hasRelatedWork W2964102750 @default.
- W2804128720 hasRelatedWork W3126302662 @default.
- W2804128720 hasRelatedWork W3173091976 @default.
- W2804128720 hasRelatedWork W3212734019 @default.
- W2804128720 hasRelatedWork W323224347 @default.
- W2804128720 hasRelatedWork W2298680016 @default.
- W2804128720 hasRelatedWork W2395890103 @default.
- W2804128720 isParatext "false" @default.
- W2804128720 isRetracted "false" @default.
- W2804128720 magId "2804128720" @default.
- W2804128720 workType "article" @default.