U
Uri Stemmer
Researcher at Ben-Gurion University of the Negev
Publications - 83
Citations - 2100
Uri Stemmer is an academic researcher from Ben-Gurion University of the Negev. The author has contributed to research in topics: Differential privacy & Computer science. The author has an hindex of 20, co-authored 71 publications receiving 1601 citations. Previous affiliations of Uri Stemmer include Georgetown University & Google.
Papers
More filters
Proceedings ArticleDOI
Algorithmic stability for adaptive data analysis
TL;DR: The first upper bounds on the number of samples required to answer more general families of queries, including arbitrary low-sensitivity queries and an important class of optimization queries (alternatively, risk minimization queries), are proved.
Journal Article
Practical Locally Private Heavy Hitters
TL;DR: In this article, the authors present new practical local differentially private heavy hitters algorithms achieving optimal or near-optimal worst-case error and running time, such as TreeHist and Bitstogram.
Proceedings ArticleDOI
Differentially Private Release and Learning of Threshold Functions
TL;DR: In this article, the sample complexity of learning threshold functions with differential privacy was shown to be at most 2(1+o(1)) log * |X| samples, which grows with the size of the domain.
Posted Content
Algorithmic Stability for Adaptive Data Analysis
TL;DR: In this paper, the authors studied the problem of estimating the number of samples required to answer a sequence of adaptive queries about an unknown distribution, as a function of the type of queries and the desired level of accuracy.
Journal ArticleDOI
Private Learning and Sanitization: Pure vs. Approximate Differential Privacy
TL;DR: It is shown that the sample complexity of private learning and sanitization tasks under approximate differential privacy can be significantly lower than that under pure differential privacy.