paper-with-me

Papers

Differentially Private Optimization with Sparse Gradients

2024-04-16 · Badih Ghazi, Cristóbal Guzmán, Pritish Kamath, Ravi Kumar, Pasin Manurangsi

Motivated by applications of large embedding models, we study differentially private (DP) optimization problems under sparsity of individual gradients. We start with new near-optimal bounds for the classic mean estimation problem but with sparse data, improving upon existing algorithms particularly for the high-dimensional regime. Building on this, we obtain pure- and approximate-DP algorithms with almost optimal rates for stochastic convex optimization with sparse gradients; the former represents the first nearly dimension-independent rates for this problem. Finally, we study the approximation of stationary points for the empirical loss in approximate-DP optimization and obtain rates that depend on sparsity instead of dimension, modulo polylogarithmic factors.

📄 PDF Abstract BibTeX arXiv:2404.10881

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

The importance of feature preprocessing for differentially private linear optimization

2023-07-19 · Ziteng Sun, Ananda Theertha Suresh, Aditya Krishna Menon

Training machine learning models with differential privacy (DP) has received increasing interest in recent years. One of the most popular algorithms for training differentially private models is differentially private st…

image-classificationImage Classification

High-Dimensional Private Empirical Risk Minimization by Greedy Coordinate Descent

2022-07-04 · Paul Mangold, Aurélien Bellet, Joseph Salmon, Marc Tommasi

In this paper, we study differentially private empirical risk minimization (DP-ERM). It has been shown that the worst-case utility of DP-ERM reduces polynomially as the dimension increases. This is a major obstacle to pr…

Vocal Bursts Intensity Prediction

Improving Differentially Private SGD via Randomly Sparsified Gradients

2021-12-01 · Junyi Zhu, Matthew B. Blaschko

Differentially private stochastic gradient descent (DP-SGD) has been widely adopted in deep learning to provide rigorously defined privacy, which requires gradient clipping to bound the maximum norm of individual gradien…

Federated Learning

Scaling Private Deep Learning with Low-Rank and Sparse Gradients

2022-07-06 · Ryuichi Ito, Seng Pei Liew, Tsubasa Takahashi, Yuya Sasaki 외

Applying Differentially Private Stochastic Gradient Descent (DPSGD) to training modern, large-scale neural networks such as transformer-based models is a challenging task, as the magnitude of noise added to the gradients…

Deep Learning

DP-FedSOFIM: Differentially Private Federated Stochastic Optimization using Regularized Fisher Information Matrix

2026-01-14 · Sidhant Nair, Tanmay Sen, Mrinmay Sen, Sayantan Banerjee arxiv

Differentially private federated learning (DP-FL) often suffers from slow convergence under tight privacy budgets because the noise required for privacy preservation degrades gradient quality. Although second-order optim…

Stochastic OptimizationFederated Learning