Matches in SemOpenAlex for { <https://semopenalex.org/work/W3202122949> ?p ?o ?g. }
- W3202122949 endingPage "1115" @default.
- W3202122949 startingPage "1082" @default.
- W3202122949 abstract "In a world where artificial intelligence and data science become omnipresent, data sharing is increasingly locking horns with data-privacy concerns. Differential privacy has emerged as a rigorous framework for protecting individual privacy in a statistical database, while releasing useful statistical information about the database. The standard way to implement differential privacy is to inject a sufficient amount of noise into the data. However, in addition to other limitations of differential privacy, this process of adding noise will affect data accuracy and utility. Another approach to enable privacy in data sharing is based on the concept of synthetic data. The goal of synthetic data is to create an as-realistic-as-possible dataset, one that not only maintains the nuances of the original data, but does so without risk of exposing sensitive information. The combination of differential privacy with synthetic data has been suggested as a best-of-both-worlds solutions. In this work, we propose the first noisefree method to construct differentially private synthetic data; we do this through a mechanism called “private sampling.” Using the Boolean cube as benchmark data model, we derive explicit bounds on accuracy and privacy of the constructed synthetic data. The key mathematical tools are hypercontractivity, duality, and empirical processes. A core ingredient of our private sampling mechanism is a rigorous “marginal correction” method, which has the remarkable property that importance reweighting can be utilized to exactly match the marginals of the sample to the marginals of the population." @default.
- W3202122949 created "2021-10-11" @default.
- W3202122949 creator A5034076533 @default.
- W3202122949 creator A5070281692 @default.
- W3202122949 creator A5080565728 @default.
- W3202122949 date "2022-08-22" @default.
- W3202122949 modified "2023-10-09" @default.
- W3202122949 title "Private Sampling: A Noiseless Approach for Generating Differentially Private Synthetic Data" @default.
- W3202122949 cites W1587575659 @default.
- W3202122949 cites W1604035549 @default.
- W3202122949 cites W1873763122 @default.
- W3202122949 cites W1975247808 @default.
- W3202122949 cites W1977843657 @default.
- W3202122949 cites W1985310469 @default.
- W3202122949 cites W2042469398 @default.
- W3202122949 cites W2064868049 @default.
- W3202122949 cites W2103958416 @default.
- W3202122949 cites W2123733729 @default.
- W3202122949 cites W2154466129 @default.
- W3202122949 cites W2159024459 @default.
- W3202122949 cites W2161229593 @default.
- W3202122949 cites W2921914364 @default.
- W3202122949 cites W2943118732 @default.
- W3202122949 cites W2950343740 @default.
- W3202122949 cites W2961396908 @default.
- W3202122949 cites W2963881987 @default.
- W3202122949 cites W2996889063 @default.
- W3202122949 cites W3003636647 @default.
- W3202122949 cites W3025816195 @default.
- W3202122949 cites W3102754027 @default.
- W3202122949 cites W4205228770 @default.
- W3202122949 cites W4250954493 @default.
- W3202122949 doi "https://doi.org/10.1137/21m1449944" @default.
- W3202122949 hasPublicationYear "2022" @default.
- W3202122949 type Work @default.
- W3202122949 sameAs 3202122949 @default.
- W3202122949 citedByCount "2" @default.
- W3202122949 countsByYear W32021229492022 @default.
- W3202122949 countsByYear W32021229492023 @default.
- W3202122949 crossrefType "journal-article" @default.
- W3202122949 hasAuthorship W3202122949A5034076533 @default.
- W3202122949 hasAuthorship W3202122949A5070281692 @default.
- W3202122949 hasAuthorship W3202122949A5080565728 @default.
- W3202122949 hasBestOaLocation W32021229491 @default.
- W3202122949 hasConcept C106131492 @default.
- W3202122949 hasConcept C11413529 @default.
- W3202122949 hasConcept C123201435 @default.
- W3202122949 hasConcept C124101348 @default.
- W3202122949 hasConcept C140779682 @default.
- W3202122949 hasConcept C142724271 @default.
- W3202122949 hasConcept C160920958 @default.
- W3202122949 hasConcept C199360897 @default.
- W3202122949 hasConcept C204787440 @default.
- W3202122949 hasConcept C23130292 @default.
- W3202122949 hasConcept C2779965156 @default.
- W3202122949 hasConcept C2780801425 @default.
- W3202122949 hasConcept C31972630 @default.
- W3202122949 hasConcept C38652104 @default.
- W3202122949 hasConcept C41008148 @default.
- W3202122949 hasConcept C71924100 @default.
- W3202122949 hasConcept C80444323 @default.
- W3202122949 hasConceptScore W3202122949C106131492 @default.
- W3202122949 hasConceptScore W3202122949C11413529 @default.
- W3202122949 hasConceptScore W3202122949C123201435 @default.
- W3202122949 hasConceptScore W3202122949C124101348 @default.
- W3202122949 hasConceptScore W3202122949C140779682 @default.
- W3202122949 hasConceptScore W3202122949C142724271 @default.
- W3202122949 hasConceptScore W3202122949C160920958 @default.
- W3202122949 hasConceptScore W3202122949C199360897 @default.
- W3202122949 hasConceptScore W3202122949C204787440 @default.
- W3202122949 hasConceptScore W3202122949C23130292 @default.
- W3202122949 hasConceptScore W3202122949C2779965156 @default.
- W3202122949 hasConceptScore W3202122949C2780801425 @default.
- W3202122949 hasConceptScore W3202122949C31972630 @default.
- W3202122949 hasConceptScore W3202122949C38652104 @default.
- W3202122949 hasConceptScore W3202122949C41008148 @default.
- W3202122949 hasConceptScore W3202122949C71924100 @default.
- W3202122949 hasConceptScore W3202122949C80444323 @default.
- W3202122949 hasFunder F4320306076 @default.
- W3202122949 hasFunder F4320332447 @default.
- W3202122949 hasIssue "3" @default.
- W3202122949 hasLocation W32021229491 @default.
- W3202122949 hasLocation W32021229492 @default.
- W3202122949 hasOpenAccess W3202122949 @default.
- W3202122949 hasPrimaryLocation W32021229491 @default.
- W3202122949 hasRelatedWork W2288802430 @default.
- W3202122949 hasRelatedWork W2623059953 @default.
- W3202122949 hasRelatedWork W2783298166 @default.
- W3202122949 hasRelatedWork W2913962591 @default.
- W3202122949 hasRelatedWork W3005947044 @default.
- W3202122949 hasRelatedWork W3112482351 @default.
- W3202122949 hasRelatedWork W3169602225 @default.
- W3202122949 hasRelatedWork W4286950335 @default.
- W3202122949 hasRelatedWork W4290845189 @default.
- W3202122949 hasRelatedWork W4379919658 @default.
- W3202122949 hasVolume "4" @default.
- W3202122949 isParatext "false" @default.
- W3202122949 isRetracted "false" @default.