Matches in SemOpenAlex for { <https://semopenalex.org/work/W3166335111> ?p ?o ?g. }
- W3166335111 abstract "We propose the use of low bit-depth Sigma-Delta and distributed noise-shaping methods for quantizing the Random Fourier features (RFFs) associated with shift-invariant kernels. We prove that our quantized RFFs -- even in the case of $1$-bit quantization -- allow a high accuracy approximation of the underlying kernels, and the approximation error decays at least polynomially fast as the dimension of the RFFs increases. We also show that the quantized RFFs can be further compressed, yielding an excellent trade-off between memory use and accuracy. Namely, the approximation error now decays exponentially as a function of the bits used. Moreover, we empirically show by testing the performance of our methods on several machine learning tasks that our method compares favorably to other state of the art quantization methods in this context." @default.
- W3166335111 created "2021-06-22" @default.
- W3166335111 creator A5032088513 @default.
- W3166335111 creator A5049178654 @default.
- W3166335111 creator A5055778695 @default.
- W3166335111 date "2021-06-04" @default.
- W3166335111 modified "2023-10-16" @default.
- W3166335111 title "Sigma-Delta and Distributed Noise-Shaping Quantization Methods for Random Fourier Features" @default.
- W3166335111 cites W143004564 @default.
- W3166335111 cites W1503398984 @default.
- W3166335111 cites W1510073064 @default.
- W3166335111 cites W1526741802 @default.
- W3166335111 cites W1527312120 @default.
- W3166335111 cites W1560724230 @default.
- W3166335111 cites W1597666193 @default.
- W3166335111 cites W1672244770 @default.
- W3166335111 cites W1698155719 @default.
- W3166335111 cites W1989877067 @default.
- W3166335111 cites W2015500481 @default.
- W3166335111 cites W2020455335 @default.
- W3166335111 cites W2047278710 @default.
- W3166335111 cites W2060600745 @default.
- W3166335111 cites W2122645855 @default.
- W3166335111 cites W2124331852 @default.
- W3166335111 cites W2144902422 @default.
- W3166335111 cites W2152981240 @default.
- W3166335111 cites W2163296328 @default.
- W3166335111 cites W2164568552 @default.
- W3166335111 cites W2171155677 @default.
- W3166335111 cites W2212660284 @default.
- W3166335111 cites W2278578264 @default.
- W3166335111 cites W2568875900 @default.
- W3166335111 cites W2579029485 @default.
- W3166335111 cites W2659372015 @default.
- W3166335111 cites W2963013450 @default.
- W3166335111 cites W2963173208 @default.
- W3166335111 cites W2963459001 @default.
- W3166335111 cites W2963709899 @default.
- W3166335111 cites W2964324431 @default.
- W3166335111 cites W3016462744 @default.
- W3166335111 cites W3019297623 @default.
- W3166335111 cites W3128009726 @default.
- W3166335111 cites W3130001316 @default.
- W3166335111 cites W2592414023 @default.
- W3166335111 cites W2898071315 @default.
- W3166335111 doi "https://doi.org/10.48550/arxiv.2106.02614" @default.
- W3166335111 hasPublicationYear "2021" @default.
- W3166335111 type Work @default.
- W3166335111 sameAs 3166335111 @default.
- W3166335111 citedByCount "1" @default.
- W3166335111 countsByYear W31663351112021 @default.
- W3166335111 crossrefType "posted-content" @default.
- W3166335111 hasAuthorship W3166335111A5032088513 @default.
- W3166335111 hasAuthorship W3166335111A5049178654 @default.
- W3166335111 hasAuthorship W3166335111A5055778695 @default.
- W3166335111 hasBestOaLocation W31663351111 @default.
- W3166335111 hasConcept C102519508 @default.
- W3166335111 hasConcept C11413529 @default.
- W3166335111 hasConcept C115961682 @default.
- W3166335111 hasConcept C121332964 @default.
- W3166335111 hasConcept C134306372 @default.
- W3166335111 hasConcept C154945302 @default.
- W3166335111 hasConcept C190470478 @default.
- W3166335111 hasConcept C202444582 @default.
- W3166335111 hasConcept C2778049214 @default.
- W3166335111 hasConcept C28855332 @default.
- W3166335111 hasConcept C2986577269 @default.
- W3166335111 hasConcept C33676613 @default.
- W3166335111 hasConcept C33923547 @default.
- W3166335111 hasConcept C37914503 @default.
- W3166335111 hasConcept C41008148 @default.
- W3166335111 hasConcept C62520636 @default.
- W3166335111 hasConcept C99498987 @default.
- W3166335111 hasConceptScore W3166335111C102519508 @default.
- W3166335111 hasConceptScore W3166335111C11413529 @default.
- W3166335111 hasConceptScore W3166335111C115961682 @default.
- W3166335111 hasConceptScore W3166335111C121332964 @default.
- W3166335111 hasConceptScore W3166335111C134306372 @default.
- W3166335111 hasConceptScore W3166335111C154945302 @default.
- W3166335111 hasConceptScore W3166335111C190470478 @default.
- W3166335111 hasConceptScore W3166335111C202444582 @default.
- W3166335111 hasConceptScore W3166335111C2778049214 @default.
- W3166335111 hasConceptScore W3166335111C28855332 @default.
- W3166335111 hasConceptScore W3166335111C2986577269 @default.
- W3166335111 hasConceptScore W3166335111C33676613 @default.
- W3166335111 hasConceptScore W3166335111C33923547 @default.
- W3166335111 hasConceptScore W3166335111C37914503 @default.
- W3166335111 hasConceptScore W3166335111C41008148 @default.
- W3166335111 hasConceptScore W3166335111C62520636 @default.
- W3166335111 hasConceptScore W3166335111C99498987 @default.
- W3166335111 hasLocation W31663351111 @default.
- W3166335111 hasOpenAccess W3166335111 @default.
- W3166335111 hasPrimaryLocation W31663351111 @default.
- W3166335111 hasRelatedWork W1525977608 @default.
- W3166335111 hasRelatedWork W1981482516 @default.
- W3166335111 hasRelatedWork W2005930910 @default.
- W3166335111 hasRelatedWork W2080397230 @default.
- W3166335111 hasRelatedWork W2088281665 @default.
- W3166335111 hasRelatedWork W2090002631 @default.
- W3166335111 hasRelatedWork W2168553558 @default.