English

Differentially Private Optimization for Smooth Nonconvex ERM

Machine Learning 2023-06-12 v2 Cryptography and Security Optimization and Control Machine Learning

Abstract

We develop simple differentially private optimization algorithms that move along directions of (expected) descent to find an approximate second-order solution for nonconvex ERM. We use line search, mini-batching, and a two-phase strategy to improve the speed and practicality of the algorithm. Numerical experiments demonstrate the effectiveness of these approaches.

Keywords

Cite

@article{arxiv.2302.04972,
  title  = {Differentially Private Optimization for Smooth Nonconvex ERM},
  author = {Changyu Gao and Stephen J. Wright},
  journal= {arXiv preprint arXiv:2302.04972},
  year   = {2023}
}
R2 v1 2026-06-28T08:36:31.772Z