MLLGMay 29, 2025

Instance-Optimality for Private KL Distribution Estimation

Apple
arXiv:2505.23620v1h-index: 43
Originality Incremental advance
AI Analysis

This work addresses the challenge of improving empirical performance in distribution estimation for privacy-sensitive applications, offering a more nuanced approach beyond worst-case analysis.

The paper tackles the problem of estimating discrete distributions under KL divergence, constructing minimax optimal private estimators and then proposing instance-optimal algorithms that achieve constant-factor optimality for individual distributions, with and without differential privacy constraints.

We study the fundamental problem of estimating an unknown discrete distribution $p$ over $d$ symbols, given $n$ i.i.d. samples from the distribution. We are interested in minimizing the KL divergence between the true distribution and the algorithm's estimate. We first construct minimax optimal private estimators. Minimax optimality however fails to shed light on an algorithm's performance on individual (non-worst-case) instances $p$ and simple minimax-optimal DP estimators can have poor empirical performance on real distributions. We then study this problem from an instance-optimality viewpoint, where the algorithm's error on $p$ is compared to the minimum achievable estimation error over a small local neighborhood of $p$. Under natural notions of local neighborhood, we propose algorithms that achieve instance-optimality up to constant factors, with and without a differential privacy constraint. Our upper bounds rely on (private) variants of the Good-Turing estimator. Our lower bounds use additive local neighborhoods that more precisely captures the hardness of distribution estimation in KL divergence, compared to ones considered in prior works.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes