Zobrazeno 1 - 10
of 54
pro vyhledávání: '"Kamalika, Chaudhuri"'
Publikováno v:
Proceedings of the 15th ACM Workshop on Artificial Intelligence and Security.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::07d2a480044e00afcb37e4b3464fc31f
https://doi.org/10.1145/3560830.3563731
https://doi.org/10.1145/3560830.3563731
Publikováno v:
IEEE Journal on Selected Areas in Information Theory. 1:745-759
This work examines a novel question: how much randomness is needed to achieve local differential privacy (LDP)? A motivating scenario is providing {\em multiple levels of privacy} to multiple analysts, either for distribution or for heavy-hitter esti
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0fe2c587070324bd12c5996fcaf1ef85
https://doi.org/10.1109/jsait.2020.3040403
https://doi.org/10.1109/jsait.2020.3040403
Publikováno v:
Twenty-Ninth International Joint Conference on Artificial Intelligence (IJCAI-20)
Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence
Journal of Artificial Intelligence Research
Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence
Journal of Artificial Intelligence Research
Many applications of Bayesian data analysis involve sensitive information, motivating methods which ensure that privacy is protected. We introduce a general privacy-preserving framework for Variational Bayes (VB), a widely used optimization-based Bay
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9f926ef81300399bdd0ad4a4f55dcae5
https://doi.org/10.1613/jair.1.11763
https://doi.org/10.1613/jair.1.11763
Autor:
Chhavi Yadav, Kamalika Chaudhuri
Publikováno v:
Communications in Computer and Information Science ISBN: 9783030937355
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::111e5ef3e4a2fef80d783724a91960b9
https://doi.org/10.1007/978-3-030-93736-2_8
https://doi.org/10.1007/978-3-030-93736-2_8
Publikováno v:
MSN
Mobile edge computing is an emerging research topic which aims at pushing the computation from the cloud to the edge devices. Most of the current machine learning (ML) algorithms, such as federated learning, are designed for homogeneous mobile networ
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f57cfefffca3192928d31a9f805721fc
https://doi.org/10.1109/msn50589.2020.00041
https://doi.org/10.1109/msn50589.2020.00041
Publikováno v:
IJCAI
Many applications of Bayesian data analysis involve sensitive information such as personal documents or medical records, motivating methods which ensure that privacy is protected. We introduce a general privacy-preserving framework for Variational Ba
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::fa0205b92d5445296bd3c0e97636be1e
https://doi.org/10.24963/ijcai.2020/705
https://doi.org/10.24963/ijcai.2020/705
Autor:
Benjamin Cosman, Westley Weimer, Kamalika Chaudhuri, Yao-Yuan Yang, Georgios Sakkas, Ranjit Jhala, Leon Medvinsky, Madeline Endres
Publikováno v:
SIGCSE
As dynamically-typed languages grow in popularity, especially among beginning programmers, there is an increased need to pinpoint their defects. Localization for novice bugs can be ambiguous: not all locations formally implicated are equally useful f
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::079a8cabdb380be5f8bffee6c267309e
https://doi.org/10.1145/3328778.3366860
https://doi.org/10.1145/3328778.3366860
Publikováno v:
Proceedings of the ACM on Programming Languages. 1:1-27
Localizing type errors is challenging in languages with global type inference, as the type checker must make assumptions about what the programmer intended to do. We introduce Nate, a data-driven approach to error localization based on supervised lea
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4f426a90d403514da2b7b7b28f1bde1b
https://doi.org/10.1145/3138818
https://doi.org/10.1145/3138818
Autor:
Claudio Gentile, Kamalika Chaudhuri
Publikováno v:
Theoretical Computer Science. 716:1-3
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4a1fbff9246b43bdab9a683d28cc5977
https://doi.org/10.1016/j.tcs.2018.02.009
https://doi.org/10.1016/j.tcs.2018.02.009
Publikováno v:
Tara Javidi
Counterfactual learning from observational data involves learning a classifier on an entire population based on data that is observed conditioned on a selection policy. This work considers this problem in an active setting, where the learner addition
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::93b6983c416f37ebf08668187c984461
http://arxiv.org/abs/1905.12791
http://arxiv.org/abs/1905.12791