English
Related papers

Related papers: Tight Lower Bounds for Locally Differentially Priv…

200 papers

We consider the binary classification problem in a setup that preserves the privacy of the original sample. We provide a privacy mechanism that is locally differentially private and then construct a classifier based on the private sample…

Statistics Theory · Mathematics 2019-12-11 Thomas Berrett , Cristina Butucea

Previous studies yielded discouraging results for item-level locally differentially private linear regression with $s^*$-sparsity assumption, where the minimax rate for $nm$ samples is $\mathcal{O}(s^{*}d / nm\varepsilon^2)$. This can be…

Machine Learning · Statistics 2024-08-09 Yuheng Ma , Ke Jia , Hanfang Yang

In this work, we study local minimax convergence estimation rates subject to $\epsilon$-differential privacy. Unlike worst-case rates, which may be conservative, algorithms that are locally minimax optimal must adapt to easy instances of…

Statistics Theory · Mathematics 2022-10-31 Audra McMillan , Adam Smith , Jon Ullman

We provide a simple and flexible framework for designing differentially private algorithms to find approximate stationary points of non-convex loss functions. Our framework is based on using a private approximate risk minimizer to "warm…

Machine Learning · Computer Science 2024-08-21 Andrew Lowy , Jonathan Ullman , Stephen J. Wright

We study the problem of estimating a set of $d$ linear queries with respect to some unknown distribution $\mathbf{p}$ over a domain $\mathcal{J}=[J]$ based on a sensitive data set of $n$ individuals under the constraint of local…

Machine Learning · Computer Science 2018-10-08 Raef Bassily

We investigate a problem of finding the minimum, in which each user has a real value and we want to estimate the minimum of these values under the local differential privacy constraint. We reveal that this problem is fundamentally…

Statistics Theory · Mathematics 2019-05-28 Kazuto Fukuchi , Chia-Mu Yu , Arashi Haishima , Jun Sakuma

We initiate the study of nonsmooth optimization problems under bounded local subgradient variation, which postulates bounded difference between (sub)gradients in small local regions around points, in either average or maximum sense. The…

Optimization and Control · Mathematics 2024-11-05 Jelena Diakonikolas , Cristóbal Guzmán

We give the proof of a tight lower bound on the probability that a binomial random variable exceeds its expected value. The inequality plays an important role in a variety of contexts, including the analysis of relative deviation bounds in…

Machine Learning · Computer Science 2013-11-12 Spencer Greenberg , Mehryar Mohri

The question of what can be computed, and how efficiently, are at the core of computer science. Not surprisingly, in distributed systems and networking research, an equally fundamental question is what can be computed in a…

Distributed, Parallel, and Cluster Computing · Computer Science 2016-04-01 Fabian Kuhn , Thomas Moscibroda , Roger Wattenhofer

We investigate the contraction properties of locally differentially private mechanisms. More specifically, we derive tight upper bounds on the divergence between $PK$ and $QK$ output distributions of an $\epsilon$-LDP mechanism $K$ in terms…

Information Theory · Computer Science 2024-05-06 Shahab Asoodeh , Huanyu Zhang

The Lipschitz constant is an important quantity that arises in analysing the convergence of gradient-based optimization methods. It is generally unclear how to estimate the Lipschitz constant of a complex model. Thus, this paper studies an…

Machine Learning · Statistics 2023-02-10 Calypso Herrera , Florian Krach , Josef Teichmann

Pairwise learning focuses on learning tasks with pairwise loss functions, depends on pairs of training instances, and naturally fits for modeling relationships between pairs of samples. In this paper, we focus on the privacy of pairwise…

Machine Learning · Computer Science 2021-06-02 Yilin Kang , Yong Liu , Jian Li , Weiping Wang

Our contribution in this paper is two folded. We consider first the case of linear programming with real coefficients and give a method which allows the computation of a new upper bound on the distance from the origin to a feasible point.…

Optimization and Control · Mathematics 2020-10-30 Beniamin Costandin , Marius Costandin , Petru Dobra

Differentially Private algorithms often need to select the best amongst many candidate options. Classical works on this selection problem require that the candidates' goodness, measured as a real-valued score function, does not change by…

Data Structures and Algorithms · Computer Science 2018-11-21 Jingcheng Liu , Kunal Talwar

We consider the problem of predicting as well as the best linear combination of d given functions in least squares regression under L^\infty constraints on the linear combination. When the input distribution is known, there already exists…

Statistics Theory · Mathematics 2011-09-14 Jean-Yves Audibert , Olivier Catoni

A wide variety of fundamental data analyses in machine learning, such as linear and logistic regression, require minimizing a convex function defined by the data. Since the data may contain sensitive information about individuals, and these…

Data Structures and Algorithms · Computer Science 2015-03-17 Jonathan Ullman

We prove a \emph{query complexity} lower bound on rank-one principal component analysis (PCA). We consider an oracle model where, given a symmetric matrix $M \in \mathbb{R}^{d \times d}$, an algorithm is allowed to make $T$ \emph{exact}…

Machine Learning · Computer Science 2017-04-18 Max Simchowitz , Ahmed El Alaoui , Benjamin Recht

We consider the problem of hypothesis testing for discrete distributions. In the standard model, where we have sample access to an underlying distribution $p$, extensive research has established optimal bounds for uniformity testing,…

Machine Learning · Computer Science 2024-12-03 Maryam Aliakbarpour , Piotr Indyk , Ronitt Rubinfeld , Sandeep Silwal

We study simple binary hypothesis testing under both local differential privacy (LDP) and communication constraints. We qualify our results as either minimax optimal or instance optimal: the former hold for the set of distribution pairs…

Statistics Theory · Mathematics 2023-12-19 Ankit Pensia , Amir R. Asadi , Varun Jog , Po-Ling Loh

We study the sample complexity of learning threshold functions under the constraint of differential privacy. It is assumed that each labeled example in the training data is the information of one individual and we would like to come up with…

Data Structures and Algorithms · Computer Science 2019-11-25 Haim Kaplan , Katrina Ligett , Yishay Mansour , Moni Naor , Uri Stemmer