Matches in SemOpenAlex for { <https://semopenalex.org/work/W3169963878> ?p ?o ?g. }
Showing items 1 to 98 of
98
with 100 items per page.
- W3169963878 abstract "Estimating and storing the covariance (or correlation) matrix of high-dimensional data is computationally challenging because both memory and computational requirements scale quadratically with the dimension. Fortunately, high-dimensional covariance matrices as observed in text, click-through, meta-genomics datasets, etc are often sparse. In this paper, we consider the problem of efficient sparse estimation of covariance matrices with possibly trillions of entries. The size of the datasets we target requires the algorithm to be online, as more than one pass over the data is prohibitive. In this paper, we propose Active Sampling Count Sketch (ASCS), an online and one-pass sketching algorithm, that recovers the large entries of the covariance matrix accurately. Count Sketch (CS), and other sub-linear compressed sensing algorithms, offer a natural solution to the problem in theory. However, vanilla CS does not work well in practice due to a low signal-to-noise ratio (SNR). At the heart of our approach is a novel active sampling strategy that increases the SNR of classical CS. We demonstrate the practicality of our algorithm with synthetic data and real-world high dimensional datasets. ASCS significantly improves over vanilla CS, demonstrating the merit of our active sampling strategy." @default.
- W3169963878 created "2021-06-22" @default.
- W3169963878 creator A5002013975 @default.
- W3169963878 creator A5003606899 @default.
- W3169963878 creator A5024993683 @default.
- W3169963878 creator A5025236320 @default.
- W3169963878 date "2021-06-09" @default.
- W3169963878 modified "2023-10-13" @default.
- W3169963878 title "Active Sampling Count Sketch (ASCS) for Online Sparse Estimation of a Trillion Scale Covariance Matrix" @default.
- W3169963878 cites W1964391232 @default.
- W3169963878 cites W1975900269 @default.
- W3169963878 cites W1980381661 @default.
- W3169963878 cites W1995436190 @default.
- W3169963878 cites W2117994680 @default.
- W3169963878 cites W2138785419 @default.
- W3169963878 cites W2153635508 @default.
- W3169963878 cites W216325278 @default.
- W3169963878 cites W2201600774 @default.
- W3169963878 cites W2263882035 @default.
- W3169963878 cites W2439904216 @default.
- W3169963878 cites W2794050961 @default.
- W3169963878 cites W2798945787 @default.
- W3169963878 cites W2883806880 @default.
- W3169963878 cites W2963765365 @default.
- W3169963878 cites W3105320479 @default.
- W3169963878 doi "https://doi.org/10.1145/3448016.3457327" @default.
- W3169963878 hasPublicationYear "2021" @default.
- W3169963878 type Work @default.
- W3169963878 sameAs 3169963878 @default.
- W3169963878 citedByCount "1" @default.
- W3169963878 countsByYear W31699638782022 @default.
- W3169963878 crossrefType "proceedings-article" @default.
- W3169963878 hasAuthorship W3169963878A5002013975 @default.
- W3169963878 hasAuthorship W3169963878A5003606899 @default.
- W3169963878 hasAuthorship W3169963878A5024993683 @default.
- W3169963878 hasAuthorship W3169963878A5025236320 @default.
- W3169963878 hasBestOaLocation W31699638781 @default.
- W3169963878 hasConcept C105795698 @default.
- W3169963878 hasConcept C106131492 @default.
- W3169963878 hasConcept C106487976 @default.
- W3169963878 hasConcept C11413529 @default.
- W3169963878 hasConcept C121332964 @default.
- W3169963878 hasConcept C124851039 @default.
- W3169963878 hasConcept C140779682 @default.
- W3169963878 hasConcept C159985019 @default.
- W3169963878 hasConcept C163716315 @default.
- W3169963878 hasConcept C178650346 @default.
- W3169963878 hasConcept C180877172 @default.
- W3169963878 hasConcept C185142706 @default.
- W3169963878 hasConcept C192562407 @default.
- W3169963878 hasConcept C202444582 @default.
- W3169963878 hasConcept C2778755073 @default.
- W3169963878 hasConcept C31972630 @default.
- W3169963878 hasConcept C33676613 @default.
- W3169963878 hasConcept C33923547 @default.
- W3169963878 hasConcept C41008148 @default.
- W3169963878 hasConcept C56372850 @default.
- W3169963878 hasConcept C62520636 @default.
- W3169963878 hasConceptScore W3169963878C105795698 @default.
- W3169963878 hasConceptScore W3169963878C106131492 @default.
- W3169963878 hasConceptScore W3169963878C106487976 @default.
- W3169963878 hasConceptScore W3169963878C11413529 @default.
- W3169963878 hasConceptScore W3169963878C121332964 @default.
- W3169963878 hasConceptScore W3169963878C124851039 @default.
- W3169963878 hasConceptScore W3169963878C140779682 @default.
- W3169963878 hasConceptScore W3169963878C159985019 @default.
- W3169963878 hasConceptScore W3169963878C163716315 @default.
- W3169963878 hasConceptScore W3169963878C178650346 @default.
- W3169963878 hasConceptScore W3169963878C180877172 @default.
- W3169963878 hasConceptScore W3169963878C185142706 @default.
- W3169963878 hasConceptScore W3169963878C192562407 @default.
- W3169963878 hasConceptScore W3169963878C202444582 @default.
- W3169963878 hasConceptScore W3169963878C2778755073 @default.
- W3169963878 hasConceptScore W3169963878C31972630 @default.
- W3169963878 hasConceptScore W3169963878C33676613 @default.
- W3169963878 hasConceptScore W3169963878C33923547 @default.
- W3169963878 hasConceptScore W3169963878C41008148 @default.
- W3169963878 hasConceptScore W3169963878C56372850 @default.
- W3169963878 hasConceptScore W3169963878C62520636 @default.
- W3169963878 hasFunder F4320306076 @default.
- W3169963878 hasLocation W31699638781 @default.
- W3169963878 hasLocation W31699638782 @default.
- W3169963878 hasOpenAccess W3169963878 @default.
- W3169963878 hasPrimaryLocation W31699638781 @default.
- W3169963878 hasRelatedWork W1910942334 @default.
- W3169963878 hasRelatedWork W2035323049 @default.
- W3169963878 hasRelatedWork W2064237292 @default.
- W3169963878 hasRelatedWork W2099216015 @default.
- W3169963878 hasRelatedWork W2158568378 @default.
- W3169963878 hasRelatedWork W2370217726 @default.
- W3169963878 hasRelatedWork W2384787007 @default.
- W3169963878 hasRelatedWork W2557331355 @default.
- W3169963878 hasRelatedWork W2800816008 @default.
- W3169963878 hasRelatedWork W3201815179 @default.
- W3169963878 isParatext "false" @default.
- W3169963878 isRetracted "false" @default.
- W3169963878 magId "3169963878" @default.
- W3169963878 workType "article" @default.