Saved in:
Bibliographic Details
Main Authors: Zampetakis, Manolis, Zhou, Felix
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.12541
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909893689081856
author Zampetakis, Manolis
Zhou, Felix
author_facet Zampetakis, Manolis
Zhou, Felix
contents We introduce a novel framework for differentially private (DP) statistical estimation via data truncation, addressing a key challenge in DP estimation when the data support is unbounded. Traditional approaches rely on problem-specific sensitivity analysis, limiting their applicability. By leveraging techniques from truncated statistics, we develop computationally efficient DP estimators for exponential family distributions, including Gaussian mean and covariance estimation, achieving near-optimal sample complexity. Previous works on exponential families only consider bounded or one-dimensional families. Our approach mitigates sensitivity through truncation while carefully correcting for the introduced bias using maximum likelihood estimation and DP stochastic gradient descent. Along the way, we establish improved uniform convergence guarantees for the log-likelihood function of exponential families, which may be of independent interest. Our results provide a general blueprint for DP algorithm design via truncated statistics.
format Preprint
id arxiv_https___arxiv_org_abs_2505_12541
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Private Statistical Estimation via Truncation
Zampetakis, Manolis
Zhou, Felix
Machine Learning
Cryptography and Security
Data Structures and Algorithms
We introduce a novel framework for differentially private (DP) statistical estimation via data truncation, addressing a key challenge in DP estimation when the data support is unbounded. Traditional approaches rely on problem-specific sensitivity analysis, limiting their applicability. By leveraging techniques from truncated statistics, we develop computationally efficient DP estimators for exponential family distributions, including Gaussian mean and covariance estimation, achieving near-optimal sample complexity. Previous works on exponential families only consider bounded or one-dimensional families. Our approach mitigates sensitivity through truncation while carefully correcting for the introduced bias using maximum likelihood estimation and DP stochastic gradient descent. Along the way, we establish improved uniform convergence guarantees for the log-likelihood function of exponential families, which may be of independent interest. Our results provide a general blueprint for DP algorithm design via truncated statistics.
title Private Statistical Estimation via Truncation
topic Machine Learning
Cryptography and Security
Data Structures and Algorithms
url https://arxiv.org/abs/2505.12541