Gradient complexity and non-stationary views of differentially private empirical risk minimization

DOI10.1016/j.tcs.2023.114259OpenAlexW4387745690MaRDI QIDQ6199392

Jinhui Xu, Di Wang

Publication date: 23 February 2024

Published in: Theoretical Computer Science (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.tcs.2023.114259

zbMATH Keywords

convex optimizationsupervised learningnon-convex optimizationdifferential privacyempirical risk minimization

Mathematics Subject Classification ID

Theory of computing (68Qxx)

Cites Work

• Unnamed Item
• Unnamed Item
• Smooth minimization of non-smooth functions
• Accelerated gradient methods for nonconvex nonlinear and stochastic programming
• The landscape of empirical risk for nonconvex losses
• Concentrated Differential Privacy: Simplifications, Extensions, and Lower Bounds
• The Algorithmic Foundations of Differential Privacy
• Katyusha: the first direct acceleration of stochastic gradient methods
• Private stochastic convex optimization: optimal rates in linear time
• A Proximal Stochastic Gradient Method with Progressive Variance Reduction
• Theory of Cryptography
• Mini-batch stochastic approximation methods for nonconvex stochastic composite optimization

This page was built for publication: Gradient complexity and non-stationary views of differentially private empirical risk minimization