← Back to all news
arXiv Machine Learning By Hang Liu, Anna Scaglione, Sean Peisert

Differentially Private Distribution Release of Gaussian Mixture Models via KL-Divergence Minimization

Read the original on arXiv Machine Learning →

The paper proposes a method for releasing Gaussian Mixture Models (GMMs) under differential privacy (DP) by minimizing Kullback‑Leibler (KL) divergence between the released and non‑private models. It jointly optimizes privacy‑budget allocation and parameter perturbations for mixture weights, means, and covariances, providing a tractable expression for KL divergence and a theoretical analysis of DP guarantees. Experiments on synthetic and real data show that the approach achieves strong privacy while preserving high utility.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Oct 5

High-Dimensional Asymptotics and Dataset Selection for Private Transfer Learning

The paper addresses the challenge of selecting external datasets for private transfer learning by modeling high‑dimensional regression with heterogeneous sources and a weighted ridge estimator. It relies solely on aggregated statistics and offers privacy guarantees under $ ho$‑zero‑concentrated differential privacy for labels or both features and labels. A deterministic equivalent of test error is derived, enabling optimization of hyperparameters and decision‑making about the utility of private external data without accessing individual records.

By Filip Kova\v{c}evi\'c, Edwige Cyffers, Stefano Sarao Mannelli, Marco Mondelli
fine-tuningsafety
More like this →