no code implementations • NAACL (PrivateNLP) 2021 • Shlomo Hoory, Amir Feder, Avichai Tendler, Sofia Erell, Alon Peled-Cohen, Itay Laish, Hootan Nakhost, Uri Stemmer, Ayelet Benjamini, Avinatan Hassidim, Yossi Matias
One method to guarantee the privacy of such individuals is to train a differentially-private language model, but this usually comes at the expense of model performance.
no code implementations • 27 Feb 2023 • Haim Kaplan, Yishay Mansour, Shay Moran, Kobbi Nissim, Uri Stemmer
In this work we introduce an interactive variant of joint differential privacy towards handling online processes in which existing privacy definitions seem too restrictive.
no code implementations • 11 Feb 2023 • Itai Dinur, Uri Stemmer, David P. Woodruff, Samson Zhou
We study the space complexity of the two related fields of differential privacy and adaptive data analysis.
no code implementations • 29 Jan 2023 • Jay Tenenbaum, Haim Kaplan, Yishay Mansour, Uri Stemmer
the counter problem) and show that the concurrent shuffle model allows for significantly improved error compared to a standard (single) shuffle model.
no code implementations • 22 Jan 2023 • Menachem Sadigurschi, Moshe Shechner, Uri Stemmer
Streaming algorithms are typically analyzed in the oblivious setting, where we assume that the input stream is fixed in advance.
no code implementations • 8 Dec 2022 • Olivier Bousquet, Haim Kaplan, Aryeh Kontorovich, Yishay Mansour, Shay Moran, Menachem Sadigurschi, Uri Stemmer
We construct a universally Bayes consistent learning rule that satisfies differential privacy (DP).
no code implementations • 11 Nov 2022 • Edith Cohen, Xin Lyu, Jelani Nelson, Tamás Sarlós, Uri Stemmer
The problem of learning threshold functions is a fundamental one in machine learning.
no code implementations • 3 Jul 2022 • Edith Cohen, Jelani Nelson, Tamás Sarlós, Uri Stemmer
When inputs are adaptive, however, an adversarial input can be constructed after $O(\ell)$ queries with the classic estimator and the best known robust estimator only supports $\tilde{O}(\ell^2)$ queries.
no code implementations • 28 Feb 2022 • Edith Cohen, Xin Lyu, Jelani Nelson, Tamás Sarlós, Moshe Shechner, Uri Stemmer
CountSketch is a popular dimensionality reduction technique that maps vectors to a lower dimension using randomized linear measurements.
no code implementations • 10 Feb 2022 • Olivier Bousquet, Amit Daniely, Haim Kaplan, Yishay Mansour, Shay Moran, Uri Stemmer
Our transformation readily implies monotone learners in a variety of contexts: for example it extends Pestov's result to classification tasks with an arbitrary number of labels.
no code implementations • 21 Jan 2022 • Aryeh Kontorovich, Menachem Sadigurschi, Uri Stemmer
The vast majority of the work on adaptive data analysis focuses on the case where the samples in the dataset are independent.
no code implementations • 29 Dec 2021 • Edith Cohen, Haim Kaplan, Yishay Mansour, Uri Stemmer, Eliad Tsfadia
Clustering is a fundamental problem in data analysis.
no code implementations • 19 Oct 2021 • Eliad Tsfadia, Edith Cohen, Haim Kaplan, Yishay Mansour, Uri Stemmer
Differentially private algorithms for common metric aggregation tasks, such as clustering or averaging, often have limited practicality due to their complexity or to the large number of data points that is required for accurate results.
no code implementations • 11 Oct 2021 • Haim Kaplan, Shachar Schnapp, Uri Stemmer
In this work we study the problem of differentially private (DP) quantiles, in which given dataset $X$ and quantiles $q_1, ..., q_m \in [0, 1]$, we want to output $m$ quantile estimations which are as close as possible to the true quantiles and preserve DP.
no code implementations • 30 Jul 2021 • Idan Attias, Edith Cohen, Moshe Shechner, Uri Stemmer
Classical streaming algorithms operate under the (not always reasonable) assumption that the input stream is fixed in advance.
1 code implementation • NeurIPS 2021 • Menachem Sadigurschi, Uri Stemmer
We revisit the fundamental problem of learning Axis-Aligned-Rectangles over a finite grid $X^d\subseteq{\mathbb{R}}^d$ with differential privacy.
no code implementations • NeurIPS 2021 • Jay Tenenbaum, Haim Kaplan, Yishay Mansour, Uri Stemmer
We give an $(\varepsilon,\delta)$-differentially private algorithm for the multi-armed bandit (MAB) problem in the shuffle model with a distribution-dependent regret of $O\left(\left(\sum_{a\in [k]:\Delta_a>0}\frac{\log T}{\Delta_a}\right)+\frac{k\sqrt{\log\frac{1}{\delta}}\log T}{\varepsilon}\right)$, and a distribution-independent regret of $O\left(\sqrt{kT\log T}+\frac{k\sqrt{\log\frac{1}{\delta}}\log T}{\varepsilon}\right)$, where $T$ is the number of rounds, $\Delta_a$ is the suboptimality gap of the arm $a$, and $k$ is the total number of arms.
no code implementations • 26 Jan 2021 • Haim Kaplan, Yishay Mansour, Kobbi Nissim, Uri Stemmer
We present a streaming problem for which every adversarially-robust streaming algorithm must use polynomial space, while there exists a classical (oblivious) streaming algorithm that uses only polylogarithmic space.
Data Structures and Algorithms
no code implementations • 25 Oct 2020 • Edith Cohen, Ofir Geri, Tamas Sarlos, Uri Stemmer
A weighted sample of keys by (a function of) frequency is a highly versatile summary that provides a sparse set of representative keys and supports approximate evaluations of query statistics.
no code implementations • 2 Oct 2020 • Haim Kaplan, Yishay Mansour, Uri Stemmer
This simple algorithm privately tests whether the value of a given query on a database is close to what we expect it to be.
no code implementations • 28 Sep 2020 • Amos Beimel, Iftach Haitner, Kobbi Nissim, Uri Stemmer
Combining this primitive with the two-round semi-honest protocol of Applebaun et al. [TCC 2018], we obtain that every randomized functionality can be computed in the shuffle model with an honest majority, in merely two rounds.
no code implementations • NeurIPS 2020 • Haim Kaplan, Yishay Mansour, Uri Stemmer, Eliad Tsfadia
We present a differentially private learner for halfspaces over a finite grid $G$ in $\mathbb{R}^d$ with sample complexity $\approx d^{2. 5}\cdot 2^{\log^*|G|}$, which improves the state-of-the-art result of [Beimel et al., COLT 2019] by a $d^2$ factor.
no code implementations • NeurIPS 2020 • Avinatan Hassidim, Haim Kaplan, Yishay Mansour, Yossi Matias, Uri Stemmer
A streaming algorithm is said to be adversarially robust if its accuracy guarantees are maintained even when the data stream is chosen maliciously, by an adaptive adversary.
no code implementations • 30 Mar 2020 • Haim Kaplan, Micha Sharir, Uri Stemmer
We study the question of how to compute a point in the convex hull of an input set $S$ of $n$ points in ${\mathbb R}^d$ in a differentially private manner.
no code implementations • 10 Mar 2020 • Noga Alon, Amos Beimel, Shay Moran, Uri Stemmer
Let~$\cH$ be a class of boolean functions and consider a {\it composed class} $\cH'$ that is derived from~$\cH$ using some arbitrary aggregation rule (for example, $\cH'$ may be the class of all 3-wise majority-votes of functions in $\cH$).
no code implementations • 18 Dec 2019 • Amos Beimel, Aleksandra Korolova, Kobbi Nissim, Or Sheffet, Uri Stemmer
Motivated by the desire to bridge the utility gap between local and trusted curator models of differential privacy for practical applications, we initiate the theoretical study of a hybrid model introduced by "Blender" [Avent et al.,\ USENIX Security '17], in which differentially private protocols of n agents that work in the local-model are assisted by a differentially private curator that has access to the data of m additional users.
no code implementations • 22 Nov 2019 • Haim Kaplan, Katrina Ligett, Yishay Mansour, Moni Naor, Uri Stemmer
This problem has received much attention recently; unlike the non-private case, where the sample complexity is independent of the domain size and just depends on the desired accuracy and confidence, for private learning the sample complexity must depend on the domain size $X$ (even for approximate differential privacy).
no code implementations • 4 Jul 2019 • Uri Stemmer
We design a new algorithm for the Euclidean $k$-means problem that operates in the local model of differential privacy.
no code implementations • 27 Feb 2019 • Amos Beimel, Shay Moran, Kobbi Nissim, Uri Stemmer
The building block for this learner is a differentially private algorithm for locating an approximate center point of $m>\mathrm{poly}(d, 2^{\log^*|X|})$ points -- a high dimensional generalization of the median function.
no code implementations • 13 Feb 2019 • Haim Kaplan, Yishay Mansour, Yossi Matias, Uri Stemmer
We present differentially private efficient algorithms for learning union of polygons in the plane (which are not necessarily convex).
no code implementations • NeurIPS 2018 • Kobbi Nissim, Adam Smith, Thomas Steinke, Uri Stemmer, Jonathan Ullman
While statistics and machine learning offers numerous methods for ensuring generalization, these methods often fail in the presence of adaptivity---the common practice in which the choice of analysis depends on previous interactions with the same dataset.
no code implementations • 6 Mar 2017 • Kobbi Nissim, Uri Stemmer
We show that differential privacy can be used to prove concentration bounds for such functions in the non-adaptive setting.
no code implementations • 19 Apr 2016 • Kobbi Nissim, Uri Stemmer, Salil Vadhan
We present a new algorithm for locating a small cluster of points with differential privacy [Dwork, McSherry, Nissim, and Smith, 2006].
no code implementations • 27 Nov 2015 • Mark Bun, Kobbi Nissim, Uri Stemmer
We investigate the direct-sum problem in the context of differentially private PAC learning: What is the sample complexity of solving $k$ learning tasks simultaneously under differential privacy, and how does this cost compare to that of solving $k$ learning tasks without privacy?
no code implementations • 8 Nov 2015 • Raef Bassily, Kobbi Nissim, Adam Smith, Thomas Steinke, Uri Stemmer, Jonathan Ullman
Specifically, suppose there is an unknown distribution $\mathbf{P}$ and a set of $n$ independent samples $\mathbf{x}$ is drawn from $\mathbf{P}$.
no code implementations • 28 Apr 2015 • Mark Bun, Kobbi Nissim, Uri Stemmer, Salil Vadhan
Our sample complexity upper and lower bounds also apply to the tasks of learning distributions with respect to Kolmogorov distance and of properly PAC learning thresholds with differential privacy.
no code implementations • 22 Apr 2015 • Kobbi Nissim, Uri Stemmer
Very recently, Bassily et al. presented an improved bound and showed that (a variant of) the private multiplicative weights algorithm can answer $k$ adaptively chosen statistical queries using sample complexity that grows logarithmically in $k$.
no code implementations • 10 Jul 2014 • Amos Beimel, Kobbi Nissim, Uri Stemmer
We show that the sample complexity of these tasks under approximate differential privacy can be significantly lower than that under pure differential privacy.
no code implementations • 10 Jul 2014 • Amos Beimel, Kobbi Nissim, Uri Stemmer
In 2008, Kasiviswanathan et al. (FOCS 2008) gave a generic construction of private learners, in which the sample complexity is (generally) higher than what is needed for non-private learners.
no code implementations • 10 Feb 2014 • Amos Beimel, Kobbi Nissim, Uri Stemmer
Kasiviswanathan et al. gave a generic construction of private learners for (finite) concept classes, with sample complexity logarithmic in the size of the concept class.