English
Related papers

Related papers: A Fast Algorithm for Adaptive Private Mean Estimat…

200 papers

We study the estimation of the covariance matrix $\Sigma$ of a $p$-dimensional normal random vector based on $n$ independent observations corrupted by additive noise. Only a general nonparametric assumption is imposed on the distribution of…

Statistics Theory · Mathematics 2018-03-28 Denis Belomestny , Mathias Trabs , Alexandre B. Tsybakov

A distributed adaptive algorithm for estimation of sparse unknown parameters in the presence of nonGaussian noise is proposed in this paper based on normalized least mean fourth (NLMF) criterion. At the first step, local adaptive NLMF…

Information Theory · Computer Science 2015-12-09 Mojtaba Hajiabadi

We consider the problem of estimating the density $g$ of identically distributed variables $X\_i$, from a sample $Z\_1, ..., Z\_n$ where $Z\_i=X\_i+\sigma\epsilon\_i$, $i=1, ..., n$ and $\sigma \epsilon\_i$ is a noise independent of $X\_i$…

Statistics Theory · Mathematics 2008-02-11 Fabienne Comte , Yves Rozenholc , Marie-Luce Taupin

We present new differentially private algorithms for learning a large-margin halfspace. In contrast to previous algorithms, which are based on either differentially private simulations of the statistical query model or on private convex…

Machine Learning · Computer Science 2020-02-25 Huy L. Nguyen , Jonathan Ullman , Lydia Zakynthinou

We provide the first $\widetilde{\mathcal{O}}\left(d\right)$-sample algorithm for sampling from unbounded Gaussian distributions under the constraint of $\left(\varepsilon, \delta\right)$-differential privacy. This is a quadratic…

Data Structures and Algorithms · Computer Science 2025-03-04 Valentio Iverson , Gautam Kamath , Argyris Mouzakis

We give the first polynomial-time algorithm for performing linear or polynomial regression resilient to adversarial corruptions in both examples and labels. Given a sufficiently large (polynomial-size) training set drawn i.i.d. from…

Machine Learning · Computer Science 2020-06-05 Adam Klivans , Pravesh K. Kothari , Raghu Meka

Decentralized optimization is critical for solving large-scale machine learning problems over distributed networks, where multiple nodes collaborate through local communication. In practice, the variances of stochastic gradient estimators…

Optimization and Control · Mathematics 2026-02-13 Hongxu Chen , Ke Wei , Luo Luo

We study differentially private (DP) algorithms for stochastic non-convex optimization. In this problem, the goal is to minimize the population loss over a $p$-dimensional space given $n$ i.i.d. samples drawn from a distribution. We improve…

Machine Learning · Computer Science 2020-08-12 Yingxue Zhou , Xiangyi Chen , Mingyi Hong , Zhiwei Steven Wu , Arindam Banerjee

Experimental design is a classical statistics problem and its aim is to estimate an unknown $m$-dimensional vector $\beta$ from linear measurements where a Gaussian noise is introduced in each measurement. For the combinatorial experimental…

Machine Learning · Statistics 2024-12-06 Mohit Singh , Weijun Xie

Uncertainty computation in deep learning is essential to design robust and reliable systems. Variational inference (VI) is a promising approach for such computation, but requires more effort to implement and execute compared to…

Machine Learning · Statistics 2018-08-03 Mohammad Emtiyaz Khan , Didrik Nielsen , Voot Tangkaratt , Wu Lin , Yarin Gal , Akash Srivastava

The Metropolis-Adjusted Langevin Algorithm (MALA) is a widely used Markov Chain Monte Carlo (MCMC) method for sampling from high-dimensional distributions. However, MALA relies on differentiability assumptions that restrict its…

Methodology · Statistics 2025-07-10 Ning Ning

We study the problem of learning mixtures of Gaussians with approximate differential privacy. We prove that roughly $kd^2 + k^{1.5} d^{1.75} + k^2 d$ samples suffice to learn a mixture of $k$ arbitrary $d$-dimensional Gaussians up to low…

Machine Learning · Computer Science 2024-11-05 Hassan Ashtiani , Mahbod Majid , Shyam Narayanan

Bayesian methods lie at the heart of modern data science and provide a powerful scaffolding for estimation in data-constrained settings and principled quantification and propagation of uncertainty. Yet in many real-world use cases where…

Data Structures and Algorithms · Computer Science 2026-03-20 Sitan Chen , Jingqiu Ding , Mahbod Majid , Walter McKelvie

We introduce an $(\epsilon, \delta)$-jointly differentially private algorithm for packing problems. Our algorithm not only achieves the optimal trade-off between the privacy parameter $\epsilon$ and the minimum supply requirement (up to…

Data Structures and Algorithms · Computer Science 2019-05-03 Zhiyi Huang , Xue Zhu

Importance sampling has become an indispensable strategy to speed up optimization algorithms for large-scale applications. Improved adaptive variants - using importance values defined by the complete gradient information which changes…

Machine Learning · Computer Science 2017-11-08 Sebastian U. Stich , Anant Raj , Martin Jaggi

We study efficient differentially private algorithms for estimating monotone statistics, i.e., statistics that are monotone under the addition of new observations. The starting point for our investigation is subsample-and-aggregate: a…

Cryptography and Security · Computer Science 2026-05-28 Gavin Brown , Ephraim Linder , Mahbod Majid , Vikrant Singhal

We consider the problem of estimating the number of distinct elements in a large data set (or, equivalently, the support size of the distribution induced by the data set) from a random sample of its elements. The problem occurs in many…

Machine Learning · Computer Science 2021-06-17 Talya Eden , Piotr Indyk , Shyam Narayanan , Ronitt Rubinfeld , Sandeep Silwal , Tal Wagner

We propose a numerical accountant for evaluating the tight $(\varepsilon,\delta)$-privacy loss for algorithms with discrete one dimensional output. The method is based on the privacy loss distribution formalism and it uses the recently…

Machine Learning · Statistics 2021-06-24 Antti Koskela , Joonas Jälkö , Lukas Prediger , Antti Honkela

The Metropolis-adjusted Langevin (MALA) algorithm is a sampling algorithm that incorporates the gradient of the logarithm of the target density in its proposal distribution. In an earlier joint work \citet{pill:stu:12}, the author had…

Computation · Statistics 2025-01-15 Natesh S. Pillai

We provide computationally efficient, differentially private algorithms for the classical regression settings of Least Squares Fitting, Binary Regression and Linear Regression with unbounded covariates. Prior to our work, privacy…

Cryptography and Security · Computer Science 2022-02-24 Jason Milionis , Alkis Kalavasis , Dimitris Fotakis , Stratis Ioannidis