Matches in SemOpenAlex for { <https://semopenalex.org/work/W1997690112> ?p ?o ?g. }
Showing items 1 to 98 of
98
with 100 items per page.
- W1997690112 abstract "We consider the problem of privately releasing a low dimensional approximation to a set of data records, represented as a matrix A in which each row corresponds to an individual and each column to an attribute. Our goal is to compute a subspace that captures the covariance of A as much as possible, classically known as principal component analysis (PCA). We assume that each row of A has ℓ2 norm bounded by one, and the privacy guarantee is defined with respect to addition or removal of any single row. We show that the well-known, but misnamed, randomized response algorithm, with properly tuned parameters, provides nearly optimal additive quality gap compared to the best possible singular subspace of A. We further show that when ATA has a large eigenvalue gap -- a reason often cited for PCA -- the quality improves significantly. Optimality (up to logarithmic factors) is proved using techniques inspired by the recent work of Bun, Ullman, and Vadhan on applying Tardos's fingerprinting codes to the construction of hard instances for private mechanisms for 1-way marginal queries. Along the way we define a list culling game which may be of independent interest." @default.
- W1997690112 created "2016-06-24" @default.
- W1997690112 creator A5008213441 @default.
- W1997690112 creator A5011820318 @default.
- W1997690112 creator A5066716873 @default.
- W1997690112 creator A5080065269 @default.
- W1997690112 date "2014-05-31" @default.
- W1997690112 modified "2023-10-17" @default.
- W1997690112 title "Analyze gauss" @default.
- W1997690112 cites W1557833142 @default.
- W1997690112 cites W1873763122 @default.
- W1997690112 cites W1970950689 @default.
- W1997690112 cites W1982147025 @default.
- W1997690112 cites W2009611335 @default.
- W1997690112 cites W2010523825 @default.
- W1997690112 cites W2022097286 @default.
- W1997690112 cites W2031722321 @default.
- W1997690112 cites W2043969662 @default.
- W1997690112 cites W2069317438 @default.
- W1997690112 cites W2098160578 @default.
- W1997690112 cites W2121647436 @default.
- W1997690112 cites W2124612670 @default.
- W1997690112 cites W2129812935 @default.
- W1997690112 cites W2134195444 @default.
- W1997690112 cites W2134332047 @default.
- W1997690112 cites W2138865266 @default.
- W1997690112 cites W2169401877 @default.
- W1997690112 cites W2401095126 @default.
- W1997690112 cites W2611328865 @default.
- W1997690112 cites W4292022450 @default.
- W1997690112 cites W602904462 @default.
- W1997690112 doi "https://doi.org/10.1145/2591796.2591883" @default.
- W1997690112 hasPublicationYear "2014" @default.
- W1997690112 type Work @default.
- W1997690112 sameAs 1997690112 @default.
- W1997690112 citedByCount "135" @default.
- W1997690112 countsByYear W19976901122013 @default.
- W1997690112 countsByYear W19976901122014 @default.
- W1997690112 countsByYear W19976901122015 @default.
- W1997690112 countsByYear W19976901122016 @default.
- W1997690112 countsByYear W19976901122017 @default.
- W1997690112 countsByYear W19976901122018 @default.
- W1997690112 countsByYear W19976901122019 @default.
- W1997690112 countsByYear W19976901122020 @default.
- W1997690112 countsByYear W19976901122021 @default.
- W1997690112 countsByYear W19976901122022 @default.
- W1997690112 countsByYear W19976901122023 @default.
- W1997690112 crossrefType "proceedings-article" @default.
- W1997690112 hasAuthorship W1997690112A5008213441 @default.
- W1997690112 hasAuthorship W1997690112A5011820318 @default.
- W1997690112 hasAuthorship W1997690112A5066716873 @default.
- W1997690112 hasAuthorship W1997690112A5080065269 @default.
- W1997690112 hasConcept C11413529 @default.
- W1997690112 hasConcept C121332964 @default.
- W1997690112 hasConcept C126255220 @default.
- W1997690112 hasConcept C134306372 @default.
- W1997690112 hasConcept C154945302 @default.
- W1997690112 hasConcept C158693339 @default.
- W1997690112 hasConcept C24252448 @default.
- W1997690112 hasConcept C27438332 @default.
- W1997690112 hasConcept C32834561 @default.
- W1997690112 hasConcept C33923547 @default.
- W1997690112 hasConcept C34388435 @default.
- W1997690112 hasConcept C39927690 @default.
- W1997690112 hasConcept C41008148 @default.
- W1997690112 hasConcept C62520636 @default.
- W1997690112 hasConceptScore W1997690112C11413529 @default.
- W1997690112 hasConceptScore W1997690112C121332964 @default.
- W1997690112 hasConceptScore W1997690112C126255220 @default.
- W1997690112 hasConceptScore W1997690112C134306372 @default.
- W1997690112 hasConceptScore W1997690112C154945302 @default.
- W1997690112 hasConceptScore W1997690112C158693339 @default.
- W1997690112 hasConceptScore W1997690112C24252448 @default.
- W1997690112 hasConceptScore W1997690112C27438332 @default.
- W1997690112 hasConceptScore W1997690112C32834561 @default.
- W1997690112 hasConceptScore W1997690112C33923547 @default.
- W1997690112 hasConceptScore W1997690112C34388435 @default.
- W1997690112 hasConceptScore W1997690112C39927690 @default.
- W1997690112 hasConceptScore W1997690112C41008148 @default.
- W1997690112 hasConceptScore W1997690112C62520636 @default.
- W1997690112 hasFunder F4320306151 @default.
- W1997690112 hasLocation W19976901121 @default.
- W1997690112 hasOpenAccess W1997690112 @default.
- W1997690112 hasPrimaryLocation W19976901121 @default.
- W1997690112 hasRelatedWork W1999976185 @default.
- W1997690112 hasRelatedWork W2000169474 @default.
- W1997690112 hasRelatedWork W2046763563 @default.
- W1997690112 hasRelatedWork W2087977406 @default.
- W1997690112 hasRelatedWork W2166142625 @default.
- W1997690112 hasRelatedWork W2495794967 @default.
- W1997690112 hasRelatedWork W2766552659 @default.
- W1997690112 hasRelatedWork W3032982968 @default.
- W1997690112 hasRelatedWork W3147787888 @default.
- W1997690112 hasRelatedWork W4200559758 @default.
- W1997690112 isParatext "false" @default.
- W1997690112 isRetracted "false" @default.
- W1997690112 magId "1997690112" @default.
- W1997690112 workType "article" @default.