Differentially Private Algorithms for Smooth Nonconvex ERM

Changyu Gao, Stephen WrightICLR 2023 · OpenReview

Abstract

We develop simple differentially private optimization algorithms that move along directions of (expected) descent to find approximate second-order necessary solution for non-convex ERM problems. 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.
BibTeX
@inproceedings{gao2023differentially,
  author = {Changyu Gao and Stephen Wright},
  title = {{Differentially Private Algorithms for Smooth Nonconvex ERM}},
  booktitle = {International Conference on Learning Representations},
  year = {2023},
  url = {https://openreview.net/forum?id=cBNfRYPtvFY},
}

Loading related content...

Figure