English
Related papers

Related papers: Near-optimal algorithms for private estimation and…

200 papers

This work presents a statistically principled method for estimating the required number of instances in the experimental comparison of multiple algorithms on a given problem class of interest. This approach generalises earlier results by…

Methodology · Statistics 2019-08-06 Felipe Campelo , Elizabeth F. Wanner

We show a new lower bound on the sample complexity of $(\varepsilon, \delta)$-differentially private algorithms that accurately answer statistical queries on high-dimensional databases. The novelty of our bound is that it depends optimally…

Data Structures and Algorithms · Computer Science 2015-01-27 Thomas Steinke , Jonathan Ullman

The computational equivalence between approximate counting and sampling is well established for polynomial-time algorithms. The most efficient general reduction from counting to sampling is achieved via simulated annealing, where the…

Data Structures and Algorithms · Computer Science 2026-04-03 David G. Harris , Vladimir Kolmogorov , Hongyang Liu , Yitong Yin , Yiyao Zhang

We present a fast, differentially private algorithm for high-dimensional covariance-aware mean estimation with nearly optimal sample complexity. Only exponential-time estimators were previously known to achieve this guarantee. Given $n$…

Machine Learning · Computer Science 2025-11-26 Gavin Brown , Samuel B. Hopkins , Adam Smith

Although robust learning and local differential privacy are both widely studied fields of research, combining the two settings is just starting to be explored. We consider the problem of estimating a discrete distribution in total variation…

Statistics Theory · Mathematics 2022-04-21 Julien Chhor , Flore Sentenac

Given $iid$ observations from an unknown absolute continuous distribution defined on some domain $\Omega$, we propose a nonparametric method to learn a piecewise constant function to approximate the underlying probability density function.…

Machine Learning · Statistics 2018-03-13 Dangna Li , Kun Yang , Wing Hung Wong

The approximation of a discrete probability distribution $\mathbf{t}$ by an $M$-type distribution $\mathbf{p}$ is considered. The approximation error is measured by the informational divergence $\mathbb{D}(\mathbf{t}\Vert\mathbf{p})$, which…

Information Theory · Computer Science 2016-07-28 Bernhard C. Geiger , Georg Böcherer

This paper considers the problem of minimizing the time average of a controlled stochastic process subject to multiple time average constraints on other related processes. The probability distribution of the random events in the system is…

Optimization and Control · Mathematics 2016-12-20 Xiaohan Wei , Hao Yu , Michael J. Neely

Uniformity testing, or testing whether independent observations are uniformly distributed, is the prototypical question in distribution testing. Over the past years, a line of work has been focusing on uniformity testing under privacy…

Data Structures and Algorithms · Computer Science 2021-10-19 Clément L. Canonne , Hongyi Lyu

Motivated by growing concerns over ensuring privacy on social networks, we develop new algorithms and impossibility results for fitting complex statistical models to network data subject to rigorous privacy guarantees. We consider the…

Statistics Theory · Mathematics 2018-10-05 Christian Borgs , Jennifer Chayes , Adam Smith , Ilias Zadik

Differential privacy (DP) is a rigorous notion of data privacy, used for private statistics. The canonical algorithm for differentially private mean estimation is to first clip the samples to a bounded range and then add noise to their…

Statistics Theory · Mathematics 2024-10-10 Gautam Kamath , Argyris Mouzakis , Matthew Regehr , Vikrant Singhal , Thomas Steinke , Jonathan Ullman

Estimating the quantiles of a large dataset is a fundamental problem in both the streaming algorithms literature and the differential privacy literature. However, all existing private mechanisms for distribution-independent quantile…

Data Structures and Algorithms · Computer Science 2022-01-11 Daniel Alabi , Omri Ben-Eliezer , Anamay Chaturvedi

We consider the problem of learning a discrete distribution in the presence of an $\epsilon$ fraction of malicious data sources. Specifically, we consider the setting where there is some underlying distribution, $p$, and each data source…

Machine Learning · Computer Science 2017-11-23 Mingda Qiao , Gregory Valiant

Suppose one has access to oracles generating samples from two unknown probability distributions P and Q on some N-element set. How many samples does one need to test whether the two distributions are close or far from each other in the…

Quantum Physics · Physics 2011-12-01 Sergey Bravyi , Aram W. Harrow , Avinatan Hassidim

We find separation rates for testing multinomial or more general discrete distributions under the constraint of local differential privacy. We construct efficient randomized algorithms and test procedures, in both the case where only…

Statistics Theory · Mathematics 2020-05-27 Thomas B. Berrett , Cristina Butucea

Let $p$ be an unknown and arbitrary probability distribution over $[0,1)$. We consider the problem of {\em density estimation}, in which a learning algorithm is given i.i.d. draws from $p$ and must (with high probability) output a…

Machine Learning · Computer Science 2014-11-04 Siu-On Chan , Ilias Diakonikolas , Rocco A. Servedio , Xiaorui Sun

We consider the problem of estimating the partition function $Z(\beta)=\sum_x \exp(\beta(H(x))$ of a Gibbs distribution with the Hamiltonian $H:\Omega\rightarrow\{0\}\cup[1,n]$. As shown in [Harris & Kolmogorov 2024], the log-ratio $q=\ln…

Probability · Mathematics 2026-04-06 David G. Harris , Vladimir Kolmogorov

We develop a near-optimal testing procedure under the framework of Gaussian differential privacy for simple as well as one- and two-sided tests under monotone likelihood ratio conditions. Our mechanism is based on a private mean estimator…

Machine Learning · Statistics 2026-01-30 Yu-Wei Chen , Raghu Pasupathy , Jordan Awan

Frequency estimation, a.k.a. histograms, is a workhorse of data analysis, and as such has been thoroughly studied under differentially privacy. In particular, computing histograms in the \emph{local} model of privacy has been the focus of a…

Data Structures and Algorithms · Computer Science 2024-09-05 Clément L. Canonne , Abigail Gentle

Consider a family of distributions $\{\pi_{\beta}\}$ where $X\sim\pi_{\beta}$ means that $\mathbb{P}(X=x)=\exp(-\beta H(x))/Z(\beta)$. Here $Z(\beta)$ is the proper normalizing constant, equal to $\sum_x\exp(-\beta H(x))$. Then…

Probability · Mathematics 2015-03-19 Mark Huber