Author

Uri Stemmer

h-index 26 View on Semantic Scholar

We have 3 of 79 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Sep 2026

Machine Unlearning as Private Retroactive Algorithms

Machine unlearning typically aims to emulate retraining from scratch: upon a deletion request, the unlearning algorithm should produce an outcome that would have been obtained had the deleted point never been included. Recent work has shown that this emulation requirement carries no meaningful privacy semantics against...

Haim Kaplan, R. Kohen, Yishay Mansour et al. · 0 citations

#machine learning Preprint Sep 2026

Vanilla Policy Optimization Is Both Optimal and Differentially Private for Stochastic Contextual Bandits

This work develops a batched version of vanilla policy optimization using only $O(\log T)$ regression calls and policy switches, and shows how private regression oracles yield differentially private contextual bandit algorithms without composition across batches.

Idan Attias, Orin Levy, Alexander Ryabchenko et al. · 0 citations

Preprint Jul 2026

Is Randomness Necessary for Adaptive Data Analysis?

It is shown that randomness is strictly necessary to answer a non-trivial number of adaptive queries: when the analyst is unbounded, any deterministic mechanism can be forced to fail after just $k = \tilde{O}(n)$ queries.

Edith Cohen, Haim Kaplan, Yishay Mansour et al. · 0 citations