← Back to all news
arXiv Machine Learning By Haruka Tanzawa, Ayaka Sakata

Stabilizing Private LASSO under Heterogeneous Covariates via Anisotropic Objective Perturbation

Read the original on arXiv Machine Learning →

The paper investigates high‑dimensional LASSO under differential privacy using objective perturbation when covariates have heterogeneous scales. It introduces a Gram‑based anisotropic objective perturbation that counteracts the distortion caused by covariate heterogeneity, restoring isotropy in the estimation process. Through an Approximate Message Passing framework and state evolution analysis, the authors show that this approach stabilizes convergence and improves both statistical efficiency and privacy performance compared to standard uniform noise injection.

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 19

Towards Hyperparameter Transfer for Differentially Private Optimization

The paper introduces DP‑µP, a framework that extends Maximal Update Parametrization to differential privacy settings. By analyzing gradient clipping, noise injection, and feature learning, it derives a signal‑to‑noise ratio condition and spectral scaling rules for DP‑SGD, DP‑Adam, and DP‑Muon optimizers. Experiments show that DP‑µP enables zero‑shot transfer of learning rates across model widths on MLP, ViT, and GPT‑2, matching or surpassing tuned baselines while cutting computational costs.

By Tianze Wang, Zhiqi Bu, Linjun Zhang
llmssafety
More like this →
arXiv Machine Learning
Oct 16

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

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.

By Hang Liu, Anna Scaglione, Sean Peisert
multimodalsafety
More like this →