Matches in SemOpenAlex for { <https://semopenalex.org/work/W4294244666> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W4294244666 abstract "We consider an efficient computational framework for speeding up several machine learning algorithms with almost no loss of accuracy. The proposed framework relies on projections via structured matrices that we call Structured Spinners, which are formed as products of three structured matrix-blocks that incorporate rotations. The approach is highly generic, i.e. i) structured matrices under consideration can either be fully-randomized or learned, ii) our structured family contains as special cases all previously considered structured schemes, iii) the setting extends to the non-linear case where the projections are followed by non-linear functions, and iv) the method finds numerous applications including kernel approximations via random feature maps, dimensionality reduction algorithms, new fast cross-polytope LSH techniques, deep learning, convex optimization algorithms via Newton sketches, quantization with random projection trees, and more. The proposed framework comes with theoretical guarantees characterizing the capacity of the structured model in reference to its unstructured counterpart and is based on a general theoretical principle that we describe in the paper. As a consequence of our theoretical analysis, we provide the first theoretical guarantees for one of the most efficient existing LSH algorithms based on the HD3HD2HD1 structured matrix [Andoni et al., 2015]. The exhaustive experimental evaluation confirms the accuracy and efficiency of structured spinners for a variety of different applications." @default.
- W4294244666 created "2022-09-02" @default.
- W4294244666 creator A5001616259 @default.
- W4294244666 creator A5003144510 @default.
- W4294244666 creator A5006452373 @default.
- W4294244666 creator A5010293904 @default.
- W4294244666 creator A5026104258 @default.
- W4294244666 creator A5031842812 @default.
- W4294244666 creator A5059969352 @default.
- W4294244666 creator A5066189345 @default.
- W4294244666 creator A5082122135 @default.
- W4294244666 date "2016-10-19" @default.
- W4294244666 modified "2023-10-18" @default.
- W4294244666 title "Structured adaptive and random spinners for fast machine learning computations" @default.
- W4294244666 doi "https://doi.org/10.48550/arxiv.1610.06209" @default.
- W4294244666 hasPublicationYear "2016" @default.
- W4294244666 type Work @default.
- W4294244666 citedByCount "0" @default.
- W4294244666 crossrefType "posted-content" @default.
- W4294244666 hasAuthorship W4294244666A5001616259 @default.
- W4294244666 hasAuthorship W4294244666A5003144510 @default.
- W4294244666 hasAuthorship W4294244666A5006452373 @default.
- W4294244666 hasAuthorship W4294244666A5010293904 @default.
- W4294244666 hasAuthorship W4294244666A5026104258 @default.
- W4294244666 hasAuthorship W4294244666A5031842812 @default.
- W4294244666 hasAuthorship W4294244666A5059969352 @default.
- W4294244666 hasAuthorship W4294244666A5066189345 @default.
- W4294244666 hasAuthorship W4294244666A5082122135 @default.
- W4294244666 hasBestOaLocation W42942446661 @default.
- W4294244666 hasConcept C111030470 @default.
- W4294244666 hasConcept C11413529 @default.
- W4294244666 hasConcept C121332964 @default.
- W4294244666 hasConcept C154945302 @default.
- W4294244666 hasConcept C158693339 @default.
- W4294244666 hasConcept C163716315 @default.
- W4294244666 hasConcept C22367795 @default.
- W4294244666 hasConcept C2777036070 @default.
- W4294244666 hasConcept C2778459887 @default.
- W4294244666 hasConcept C41008148 @default.
- W4294244666 hasConcept C45374587 @default.
- W4294244666 hasConcept C62520636 @default.
- W4294244666 hasConcept C64812099 @default.
- W4294244666 hasConcept C70518039 @default.
- W4294244666 hasConcept C80444323 @default.
- W4294244666 hasConceptScore W4294244666C111030470 @default.
- W4294244666 hasConceptScore W4294244666C11413529 @default.
- W4294244666 hasConceptScore W4294244666C121332964 @default.
- W4294244666 hasConceptScore W4294244666C154945302 @default.
- W4294244666 hasConceptScore W4294244666C158693339 @default.
- W4294244666 hasConceptScore W4294244666C163716315 @default.
- W4294244666 hasConceptScore W4294244666C22367795 @default.
- W4294244666 hasConceptScore W4294244666C2777036070 @default.
- W4294244666 hasConceptScore W4294244666C2778459887 @default.
- W4294244666 hasConceptScore W4294244666C41008148 @default.
- W4294244666 hasConceptScore W4294244666C45374587 @default.
- W4294244666 hasConceptScore W4294244666C62520636 @default.
- W4294244666 hasConceptScore W4294244666C64812099 @default.
- W4294244666 hasConceptScore W4294244666C70518039 @default.
- W4294244666 hasConceptScore W4294244666C80444323 @default.
- W4294244666 hasLocation W42942446661 @default.
- W4294244666 hasOpenAccess W4294244666 @default.
- W4294244666 hasPrimaryLocation W42942446661 @default.
- W4294244666 hasRelatedWork W162023102 @default.
- W4294244666 hasRelatedWork W2089497633 @default.
- W4294244666 hasRelatedWork W2100681428 @default.
- W4294244666 hasRelatedWork W2141406155 @default.
- W4294244666 hasRelatedWork W2953112822 @default.
- W4294244666 hasRelatedWork W3035891470 @default.
- W4294244666 hasRelatedWork W3102427307 @default.
- W4294244666 hasRelatedWork W4287755309 @default.
- W4294244666 hasRelatedWork W4294244666 @default.
- W4294244666 hasRelatedWork W4300605969 @default.
- W4294244666 isParatext "false" @default.
- W4294244666 isRetracted "false" @default.
- W4294244666 workType "article" @default.