Matches in SemOpenAlex for { <https://semopenalex.org/work/W3208367282> ?p ?o ?g. }
- W3208367282 abstract "Random projection (RP) have recently emerged as popular techniques in themachine learning community for their ability in reducing the dimension of veryhigh-dimensional tensors. Following the work in [29], we consider a tensorizedrandom projection relying on Tensor Train (TT) decomposition where each elementof the core tensors is drawn from a Rademacher distribution. Our theoreticalresults reveal that the Gaussian low-rank tensor represented in compressed formin TT format in [29] can be replaced by a TT tensor with core elements drawnfrom a Rademacher distribution with the same embedding size. Experiments onsynthetic data demonstrate that tensorized Rademacher RP can outperform thetensorized Gaussian RP studied in [29]. In addition, we show both theoreticallyand experimentally, that the tensorized RP in the Matrix Product Operator (MPO)format proposed in [5] for performing SVD on large matrices is not a Johnson-Lindenstrauss transform (JLT) and therefore not a well-suited random projectionmap" @default.
- W3208367282 created "2021-11-08" @default.
- W3208367282 creator A5023766963 @default.
- W3208367282 creator A5074636191 @default.
- W3208367282 date "2021-10-26" @default.
- W3208367282 modified "2023-10-01" @default.
- W3208367282 title "Rademacher Random Projections with Tensor Networks" @default.
- W3208367282 cites W1246381107 @default.
- W3208367282 cites W1577871831 @default.
- W3208367282 cites W1798945469 @default.
- W3208367282 cites W1873349594 @default.
- W3208367282 cites W1963826206 @default.
- W3208367282 cites W1993482030 @default.
- W3208367282 cites W2024165284 @default.
- W3208367282 cites W2037757210 @default.
- W3208367282 cites W2041836310 @default.
- W3208367282 cites W2074878962 @default.
- W3208367282 cites W2079705627 @default.
- W3208367282 cites W2089497633 @default.
- W3208367282 cites W2093813380 @default.
- W3208367282 cites W2116019049 @default.
- W3208367282 cites W2117756735 @default.
- W3208367282 cites W2136002544 @default.
- W3208367282 cites W2144414190 @default.
- W3208367282 cites W2258054274 @default.
- W3208367282 cites W2396770278 @default.
- W3208367282 cites W2469230926 @default.
- W3208367282 cites W2963389071 @default.
- W3208367282 cites W2963484322 @default.
- W3208367282 cites W2979473749 @default.
- W3208367282 cites W2991374172 @default.
- W3208367282 cites W3037725185 @default.
- W3208367282 cites W3100068159 @default.
- W3208367282 cites W3148198191 @default.
- W3208367282 cites W3158200207 @default.
- W3208367282 cites W3159300313 @default.
- W3208367282 cites W387183918 @default.
- W3208367282 cites W83594344 @default.
- W3208367282 hasPublicationYear "2021" @default.
- W3208367282 type Work @default.
- W3208367282 sameAs 3208367282 @default.
- W3208367282 citedByCount "0" @default.
- W3208367282 crossrefType "posted-content" @default.
- W3208367282 hasAuthorship W3208367282A5023766963 @default.
- W3208367282 hasAuthorship W3208367282A5074636191 @default.
- W3208367282 hasConcept C11413529 @default.
- W3208367282 hasConcept C114614502 @default.
- W3208367282 hasConcept C121332964 @default.
- W3208367282 hasConcept C154945302 @default.
- W3208367282 hasConcept C155281189 @default.
- W3208367282 hasConcept C158693339 @default.
- W3208367282 hasConcept C163716315 @default.
- W3208367282 hasConcept C164226766 @default.
- W3208367282 hasConcept C202444582 @default.
- W3208367282 hasConcept C2777036070 @default.
- W3208367282 hasConcept C33676613 @default.
- W3208367282 hasConcept C33923547 @default.
- W3208367282 hasConcept C41008148 @default.
- W3208367282 hasConcept C41608201 @default.
- W3208367282 hasConcept C51255310 @default.
- W3208367282 hasConcept C57493831 @default.
- W3208367282 hasConcept C62520636 @default.
- W3208367282 hasConcept C64812099 @default.
- W3208367282 hasConceptScore W3208367282C11413529 @default.
- W3208367282 hasConceptScore W3208367282C114614502 @default.
- W3208367282 hasConceptScore W3208367282C121332964 @default.
- W3208367282 hasConceptScore W3208367282C154945302 @default.
- W3208367282 hasConceptScore W3208367282C155281189 @default.
- W3208367282 hasConceptScore W3208367282C158693339 @default.
- W3208367282 hasConceptScore W3208367282C163716315 @default.
- W3208367282 hasConceptScore W3208367282C164226766 @default.
- W3208367282 hasConceptScore W3208367282C202444582 @default.
- W3208367282 hasConceptScore W3208367282C2777036070 @default.
- W3208367282 hasConceptScore W3208367282C33676613 @default.
- W3208367282 hasConceptScore W3208367282C33923547 @default.
- W3208367282 hasConceptScore W3208367282C41008148 @default.
- W3208367282 hasConceptScore W3208367282C41608201 @default.
- W3208367282 hasConceptScore W3208367282C51255310 @default.
- W3208367282 hasConceptScore W3208367282C57493831 @default.
- W3208367282 hasConceptScore W3208367282C62520636 @default.
- W3208367282 hasConceptScore W3208367282C64812099 @default.
- W3208367282 hasLocation W32083672821 @default.
- W3208367282 hasOpenAccess W3208367282 @default.
- W3208367282 hasPrimaryLocation W32083672821 @default.
- W3208367282 hasRelatedWork W1567457275 @default.
- W3208367282 hasRelatedWork W1885038349 @default.
- W3208367282 hasRelatedWork W2126751401 @default.
- W3208367282 hasRelatedWork W2159040316 @default.
- W3208367282 hasRelatedWork W2248789255 @default.
- W3208367282 hasRelatedWork W2274728378 @default.
- W3208367282 hasRelatedWork W2431890537 @default.
- W3208367282 hasRelatedWork W2912747968 @default.
- W3208367282 hasRelatedWork W2922554710 @default.
- W3208367282 hasRelatedWork W2962950688 @default.
- W3208367282 hasRelatedWork W2963116674 @default.
- W3208367282 hasRelatedWork W2998187182 @default.
- W3208367282 hasRelatedWork W3004777528 @default.
- W3208367282 hasRelatedWork W3013892324 @default.
- W3208367282 hasRelatedWork W3045706843 @default.
- W3208367282 hasRelatedWork W3115053081 @default.