AI Chat AI Image Generator AI Video Text to Speech

Differentially Private Optimization for Smooth Nonconvex ERM

02/09/2023

∙

by Changyu Gao, et al.

∙

∙

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.

Changyu Gao
1 publication
Stephen J. Wright
25 publications

page 1

page 2

page 3

page 4

research

∙ 10/14/2021

Adaptive Differentially Private Empirical Risk Minimization

We propose an adaptive (stochastic) gradient perturbation method for dif...

12 Xiaoxia Wu, et al. ∙

research

∙ 08/05/2020

Differentially Private Accelerated Optimization Algorithms

We present two classes of differentially private optimization algorithms...

0 Nurdan Kuru, et al. ∙

research

∙ 10/12/2022

Differentially Private Online-to-Batch for Smooth Losses

We develop a new reduction that converts any online convex optimization ...

0 Qinzi Zhang, et al. ∙

research

∙ 03/19/2021

Differentially private inference via noisy optimization

We propose a general optimization-based framework for computing differen...

0 Marco Avella-Medina, et al. ∙

research

∙ 04/20/2023

DPAF: Image Synthesis via Differentially Private Aggregation in Forward Phase

Differentially private synthetic data is a promising alternative for sen...

0 Chih-Hsun Lin, et al. ∙

research

∙ 03/17/2022

Stochastic and Private Nonconvex Outlier-Robust PCA

We develop theoretically guaranteed stochastic methods for outlier-robus...

0 Tyler Maunu, et al. ∙

research

∙ 10/18/2020

Enabling Fast Differentially Private SGD via Just-in-Time Compilation and Vectorization

A common pain point in differentially private machine learning is the si...

13 Pranav Subramani, et al. ∙