Uri Stemmer
Artificial Intelligence · 2009–2020
A researcher in the Science corpus: 12 papers; trusts 79 researchers and is trusted by 84 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 226 citations into it; #2,918 of 36,961 by trust here, #4,356 by citations
- Privacy & Security — 148 citations into it; #74 of 710 by trust here, #143 by citations
- Computational Theory and Mathematics — 72 citations into it; #2,722 of 12,489 by trust here, #8,542 by citations
- Statistics and Probability — 40 citations into it
- Statistical Learning Theory — 30 citations into it; #395 of 1,040 by trust here, #319 by citations
- Algorithms & Complexity — 25 citations into it; #107 of 516 by trust here, #92 by citations
- Safety, Robustness & Interpretability — 22 citations into it; #1,412 of 2,259 by trust here, #2,049 by citations
- Computer Science Applications — 20 citations into it; #539 of 1,931 by trust here, #1,448 by citations
Whom Uri Stemmer trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Cynthia Dwork
- Kobbi Nissim
- Frank McSherry
- Raef Bassily
- Adam D. Smith
- Amos Beimel
- Moritz Hardt
- Mark Bun
- David Arthur
- Shiva Prasad Kasiviswanathan
Who trusts Uri Stemmer overall
- Mark Bun
- Vitaly Feldman
- Yatharth Dubey
- Badih Ghazi
- Aleksandra Korolova
- Jayadev Acharya
- Amos Beimel
- Kobbi Nissim
- Alisa Chang
- Gautam Kamath
Papers from Uri Stemmer's perspective
Ordered by how strongly the researchers Uri Stemmer trusts endorse each paper. Same corpus, a different order for every researcher.
- Calibrating Noise to Sensitivity in Private Data Analysis
- Revealing information while preserving privacy
- ImageNet classification with deep convolutional neural networks
- Gradient-based learning applied to document recognition
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- Towards Sharp Inapproximability For Any 2-CSP
- Practical privacy: the SuLQ framework
- Learning Multiple Layers of Features from Tiny Images
- Differential Privacy
- Privacy-Preserving Datamining on Vertically Partitioned Databases
Their papers
- On the Generalization Properties of Differential Privacy (2015) — 39 citations
- Algorithmic stability for adaptive data analysis (2015) — 304 citations
- The power of synergy in differential privacy: Combining a small curator with local randomizers (2019) — 16 citations
- Differentially Private Release and Learning of Threshold Functions (2015) — 221 citations
- Private Learning and Sanitization: Pure vs. Approximate Differential Privacy (2013) — 205 citations
- Locally Private k-Means Clustering (2019) — 70 citations
- On the Round Complexity of the Shuffle Model (2020) — 18 citations
- Clustering Algorithms for the Centralized and Local Models (2017) — 71 citations
- Heavy Hitters and the Structure of Local Privacy (2017) — 166 citations
- Simultaneous Private Learning of Multiple Concepts (2015) — 92 citations
- Characterizing the sample complexity of private learners (2013) — 82 citations
- Heavy Hitters (2009) — 268 citations