u@uri.co.il
Uri Stemmer
(אורי שטמר)
I am a faculty member at the School of Computer Science at Tel Aviv University.Previously, I was a faculty member at Ben-Gurion University, a postdoc at the Weizmann Institute of Science, and a postdoc at Harvard University. I completed my Ph.D. at Ben-Gurion University, where I was lucky to have Amos Beimel and Kobbi Nissim as my advisors.
Research Interests
Privacy-preserving data analysis, computational learning theory, algorithms.
Email:
u@uri.co.il
Newsu@uri.co.il
- New paper on private linear algebra posted on arXiv. Among other results, we present the first polynomial-time algorithm for privately finding a point in the convex hull in high dimensions.
- Our paper on defining "reconstruction" was accepted to ITCS'25!
- Program committees: TPDP 2019, ICDT 2020, ALT 2020, TCC 2020, TPDP 2020, ITC 2021, NeurIPS 2021 (area chair), ICML 2022 (area chair), NeurIPS 2022 (area chair), ICML 2023 (area chair), PODS 2024, FORC 2024, ICML 2024 (area chair), TPDP 2024, ALT 2025 (area chair), ICML 2025 (area chair)
- I taught a mini course at the Boston DP Summer School (2022). See the slides here: 1 2 3 4.
- I co-organized a STOC 2021 Workshop on Robust Streaming, Sketching, and Sampling
Teaching
Current students
- Moshe Shechner (co-advised with Edith Cohen)
- Refael Kohen
- Emma Rapoport
- Rotem Yeskin
- Menachem Sadigurschi, PhD 2023 (co-advised with Aryeh Kontorovich), now at Intent IQ
- Shachar Schnapp, PhD 2024 (co-advised with Sivan Sabato), now at PVML
Publications
[52]
On Differentially Private Linear Algebra
Haim Kaplan, Yishay Mansour, Shay Moran, Uri Stemmer, and Nitzan Tur
Haim Kaplan, Yishay Mansour, Shay Moran, Uri Stemmer, and Nitzan Tur
[51]
Data Reconstruction: When You See It and When You Don't
Edith Cohen, Haim Kaplan, Yishay Mansour, Shay Moran, Kobbi Nissim, Uri Stemmer, and Eliad Tsfadia
Edith Cohen, Haim Kaplan, Yishay Mansour, Shay Moran, Kobbi Nissim, Uri Stemmer, and Eliad Tsfadia
ITCS 2025
[50]
[49]
Lower Bounds for Differential Privacy Under Continual Observation and Online Threshold Queries
Edith Cohen, Xin Lyu, Jelani Nelson, Tamás Sarlós, and Uri Stemmer
Edith Cohen, Xin Lyu, Jelani Nelson, Tamás Sarlós, and Uri Stemmer
COLT 2024
[48]
MPC for Tech Giants (GMPC): Enabling Gulliver and the Lilliputians to Cooperate Amicably
Bar Alon, Moni Naor, Eran Omri, and Uri Stemmer
Bar Alon, Moni Naor, Eran Omri, and Uri Stemmer
CRYPTO 2024
[47]
Adaptive Data Analysis in a Balanced Adversarial Model
Kobbi Nissim, Uri Stemmer, and Eliad Tsfadia
Kobbi Nissim, Uri Stemmer, and Eliad Tsfadia
NeurIPS 2023 (Spotlight)
[46]
Private Everlasting Prediction
Moni Naor, Kobbi Nissim, Uri Stemmer, and Chao Yan
Moni Naor, Kobbi Nissim, Uri Stemmer, and Chao Yan
NeurIPS 2023 (Oral Presentation)
[45]
Black-Box Differential Privacy for Interactive ML
Haim Kaplan, Yishay Mansour, Shay Moran, Kobbi Nissim, and Uri Stemmer
Haim Kaplan, Yishay Mansour, Shay Moran, Kobbi Nissim, and Uri Stemmer
NeurIPS 2023
[44]
Relaxed Models for Adversarial Streaming: The Bounded Interruptions Model and the Advice Model
Menachem Sadigurschi, Moshe Shechner, and Uri Stemmer
Menachem Sadigurschi, Moshe Shechner, and Uri Stemmer
ESA 2023
[43]
Concurrent Shuffle Differential Privacy Under Continual Observation
Jay Tenenbaum, Haim Kaplan, Yishay Mansour, and Uri Stemmer
Jay Tenenbaum, Haim Kaplan, Yishay Mansour, and Uri Stemmer
ICML 2023
[42]
Õptimal Differentially Private Learning of Thresholds and Quasi-Concave Optimization
Edith Cohen, Xin Lyu, Jelani Nelson, Tamás Sarlós, and Uri Stemmer
Edith Cohen, Xin Lyu, Jelani Nelson, Tamás Sarlós, and Uri Stemmer
STOC 2023
[41]
On Differential Privacy and Adaptive Data Analysis with Bounded Space
Itai Dinur, Uri Stemmer, David P. Woodruff, and Samson Zhou
Itai Dinur, Uri Stemmer, David P. Woodruff, and Samson Zhou
Eurocrypt 2023
[40]
Tricking the Hashing Trick: A Tight Lower Bound on the Robustness of CountSketch to Adaptive Inputs
Edith Cohen, Jelani Nelson, Tamás Sarlós, and Uri Stemmer
Edith Cohen, Jelani Nelson, Tamás Sarlós, and Uri Stemmer
AAAI 2023
[39]
Generalized Private Selection and Testing with High Confidence
Edith Cohen, Xin Lyu, Jelani Nelson, Tamás Sarlós, and Uri Stemmer
Edith Cohen, Xin Lyu, Jelani Nelson, Tamás Sarlós, and Uri Stemmer
ITCS 2023
[38]
A Framework for Adversarial Streaming via Differential Privacy and Difference Estimators
Idan Attias, Edith Cohen, Moshe Shechner, and Uri Stemmer
Idan Attias, Edith Cohen, Moshe Shechner, and Uri Stemmer
ITCS 2023 and Algorithmica
[37]
On the Robustness of CountSketch to Adaptive Inputs
Edith Cohen, Xin Lyu, Jelani Nelson, Tamás Sarlós, Moshe Shechner, and Uri Stemmer
Edith Cohen, Xin Lyu, Jelani Nelson, Tamás Sarlós, Moshe Shechner, and Uri Stemmer
ICML 2022
[36]
Adaptive Data Analysis with Correlated Observations
Aryeh Kontorovich, Menachem Sadigurschi, and Uri Stemmer
Aryeh Kontorovich, Menachem Sadigurschi, and Uri Stemmer
ICML 2022
[35]
FriendlyCore: Practical Differentially Private Aggregation
Eliad Tsfadia, Edith Cohen, Haim Kaplan, Yishay Mansour, and Uri Stemmer
Eliad Tsfadia, Edith Cohen, Haim Kaplan, Yishay Mansour, and Uri Stemmer
ICML 2022
[34]
Differentially Private Approximate Quantiles
Haim Kaplan, Shachar Schnapp, and Uri Stemmer
Haim Kaplan, Shachar Schnapp, and Uri Stemmer
ICML 2022
[33]
Monotone Learning
Olivier Bousquet, Amit Daniely, Haim Kaplan, Yishay Mansour, Shay Moran, and Uri Stemmer
Olivier Bousquet, Amit Daniely, Haim Kaplan, Yishay Mansour, Shay Moran, and Uri Stemmer
COLT 2022
[32]
Dynamic Algorithms Against an Adaptive Adversary: Generic Constructions and Lower Bounds
Amos Beimel, Haim Kaplan, Yishay Mansour, Kobbi Nissim, Thatchaphol Saranurak, and Uri Stemmer
Amos Beimel, Haim Kaplan, Yishay Mansour, Kobbi Nissim, Thatchaphol Saranurak, and Uri Stemmer
STOC 2022
[31]
On the Sample Complexity of Privately Learning Axis-Aligned Rectangles
Menachem Sadigurschi and Uri Stemmer
Menachem Sadigurschi and Uri Stemmer
NeurIPS 2021
[30]
Differentially Private Multi-Armed Bandits in the Shuffle Model
Jay Tenenbaum, Haim Kaplan, Yishay Mansour, and Uri Stemmer
Jay Tenenbaum, Haim Kaplan, Yishay Mansour, and Uri Stemmer
NeurIPS 2021
[29]
Learning and Evaluating a Differentially Private Pre-trained Language Model
Shlomo Hoory, Amir Feder, Avichai Tendler, Sofia Erell, Alon Peled-Cohen, Itay Laish, Hootan Nakhost, Uri Stemmer, Ayelet Benjamini, Avinatan Hassidim, and Yossi Matias
Shlomo Hoory, Amir Feder, Avichai Tendler, Sofia Erell, Alon Peled-Cohen, Itay Laish, Hootan Nakhost, Uri Stemmer, Ayelet Benjamini, Avinatan Hassidim, and Yossi Matias
EMNLP Findings 2021
[28]
Separating Adaptive Streaming from Oblivious Streaming
Haim Kaplan, Yishay Mansour, Kobbi Nissim, and Uri Stemmer
Haim Kaplan, Yishay Mansour, Kobbi Nissim, and Uri Stemmer
CRYPTO 2021
[27]
[26]
Differentially-Private Clustering of Easy Instances
Edith Cohen, Haim Kaplan, Yishay Mansour, Uri Stemmer, and Eliad Tsfadia
Edith Cohen, Haim Kaplan, Yishay Mansour, Uri Stemmer, and Eliad Tsfadia
ICML 2021
[25]
Differentially Private Weighted Sampling
Edith Cohen, Ofir Geri, Tamás Sarlós, and Uri Stemmer
Edith Cohen, Ofir Geri, Tamás Sarlós, and Uri Stemmer
AISTATS 2021
[24]
Adversarially Robust Streaming Algorithms via Differential Privacy
Avinatan Hassidim, Haim Kaplan, Yishay Mansour, Yossi Matias, and Uri Stemmer
NeurIPS 2020 (Oral Presentation) and Journal of the ACM
Avinatan Hassidim, Haim Kaplan, Yishay Mansour, Yossi Matias, and Uri Stemmer
NeurIPS 2020 (Oral Presentation) and Journal of the ACM
[23]
Private Learning of Halfspaces: Simplifying the Construction and Reducing the Sample Complexity
Haim Kaplan, Yishay Mansour, Uri Stemmer, and Eliad Tsfadia
Haim Kaplan, Yishay Mansour, Uri Stemmer, and Eliad Tsfadia
NeurIPS 2020
[22]
On the Round Complexity of the Shuffle Model
Amos Beimel, Iftach Haitner, Kobbi Nissim, and Uri Stemmer
Amos Beimel, Iftach Haitner, Kobbi Nissim, and Uri Stemmer
TCC 2020
[21]
Closure Properties for Private Classification and Online Prediction
Noga Alon, Amos Beimel, Shay Moran, and Uri Stemmer
Noga Alon, Amos Beimel, Shay Moran, and Uri Stemmer
COLT 2020
[20]
Privately Learning Thresholds: Closing the Exponential Gap
Haim Kaplan, Katrina Ligett, Yishay Mansour, Moni Naor, and Uri Stemmer
Haim Kaplan, Katrina Ligett, Yishay Mansour, Moni Naor, and Uri Stemmer
COLT 2020
[19]
The power of synergy in differential privacy: Combining a small curator with local randomizers
Amos Beimel, Aleksandra Korolova, Kobbi Nissim, Or Sheffet, and Uri Stemmer
Amos Beimel, Aleksandra Korolova, Kobbi Nissim, Or Sheffet, and Uri Stemmer
ITC 2020
[18]
How to Find a Point in the Convex Hull Privately
Haim Kaplan, Micha Sharir, and Uri Stemmer
Haim Kaplan, Micha Sharir, and Uri Stemmer
SoCG 2020
[17]
Private k-Means Clustering with Stability Assumptions
Moshe Shechner, Or Sheffet, and Uri Stemmer
Moshe Shechner, Or Sheffet, and Uri Stemmer
AISTATS 2020
[16]
[15]
Differentially Private Learning of Geometric Concepts
Haim Kaplan, Yishay Mansour, Yossi Matias, and Uri Stemmer
Haim Kaplan, Yishay Mansour, Yossi Matias, and Uri Stemmer
ICML 2019 and SIAM Journal on Computing
[14]
Private Center Points and Learning of Halfspaces
Amos Beimel, Shay Moran, Kobbi Nissim, and Uri Stemmer
Amos Beimel, Shay Moran, Kobbi Nissim, and Uri Stemmer
COLT 2019
[13]
The Limits of Post-Selection Generalization
Kobbi Nissim, Adam Smith, Thomas Steinke, Uri Stemmer, and Jonathan Ullman
Kobbi Nissim, Adam Smith, Thomas Steinke, Uri Stemmer, and Jonathan Ullman
NeurIPS 2018
[12]
Differentially Private k-Means with Constant Multiplicative Error
Haim Kaplan and Uri Stemmer
NeurIPS 2018 (Spotlight)
Haim Kaplan and Uri Stemmer
NeurIPS 2018 (Spotlight)
[11]
Heavy Hitters and the Structure of Local Privacy
Mark Bun, Jelani Nelson, and Uri Stemmer
Mark Bun, Jelani Nelson, and Uri Stemmer
PODS 2018 and Transactions on Algorithms
[10]
[9]
Concentration Bounds for High Sensitivity Functions Through Differential Privacy
Kobbi Nissim and Uri Stemmer
Kobbi Nissim and Uri Stemmer
Journal of Privacy and Confidentiality
[8]
Practical Locally Private Heavy Hitters
Raef Bassily, Kobbi Nissim, Uri Stemmer, and Abhradeep Thakurta
Raef Bassily, Kobbi Nissim, Uri Stemmer, and Abhradeep Thakurta
NIPS 2017 and Journal of Machine Learning Research
→Presented at HALG 2018 (by invitation)
[7]
[6]
Algorithmic Stability for Adaptive Data Analysis
Raef Bassily, Kobbi Nissim, Adam Smith, Thomas Steinke, Uri Stemmer, and Jonathan Ullman
Raef Bassily, Kobbi Nissim, Adam Smith, Thomas Steinke, Uri Stemmer, and Jonathan Ullman
STOC 2016 and SIAM Journal on Computing (by invitation)
[5]
Simultaneous Private Learning of Multiple Concepts
Mark Bun, Kobbi Nissim, and Uri Stemmer
Mark Bun, Kobbi Nissim, and Uri Stemmer
ITCS 2016 and Journal of Machine Learning Research
[4]
Differentially Private Release and Learning of Threshold Functions
Mark Bun, Kobbi Nissim, Uri Stemmer, and Salil Vadhan
Mark Bun, Kobbi Nissim, Uri Stemmer, and Salil Vadhan
FOCS 2015
[3]
Learning Privately with Labeled and Unlabeled Examples
Amos Beimel, Kobbi Nissim, and Uri Stemmer
Amos Beimel, Kobbi Nissim, and Uri Stemmer
SODA 2015 and Algorithmica
[2]
Private Learning and Sanitization: Pure vs. Approximate Differential Privacy
Amos Beimel, Kobbi Nissim, and Uri Stemmer
Amos Beimel, Kobbi Nissim, and Uri Stemmer
RANDOM 2013 and Theory of Computing (by invitation)
[1]
Characterizing the Sample Complexity of Private Learners
Amos Beimel, Kobbi Nissim, and Uri Stemmer
Amos Beimel, Kobbi Nissim, and Uri Stemmer
ITCS 2013 and Journal of Machine Learning Research
Other Manuscripts
- Individuals and Privacy in the Eye of Data Analysis. Ph.D. Thesis
- Privacy Preserving Social Norm Nudges. Yifat Nahmias, Oren Perez, Yotam Shlomo, and Uri Stemmer. Michigan Technology Law Review
- A Note on Sanitizing Streams with Differential Privacy. Haim Kaplan and Uri Stemmer
Links
Amos Beimel, Kobbi Nissim, Moni Naor, Ilan Shallom, Ilan Orlov, Aryeh Kontorovich, Avner Stemmer, Dana Stemmer, Maya Stemmer