Differentially Private Accelerated Optimization Algorithms

DOI10.1137/20M1355847MaRDI QIDQ5080503

Mert Gürbüzbalaban, Sinan Yıldırım, Nurdan Kuru, Ş. İlker Birbil

Publication date: 31 May 2022

Published in: SIAM Journal on Optimization (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2008.01989

zbMATH Keywords

differential privacy; accelerated optimization methods

Mathematics Subject Classification ID

90C25: Convex programming

90C30: Nonlinear programming

68P27: Privacy of data

Related Items

Heavy-ball-based optimal thresholding algorithms for sparse linear inverse problems

Uses Software

• PrivateLR

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems
• Stochastic heavy ball
• Momentum and stochastic momentum for stochastic gradient, Newton, proximal point and subspace descent methods
• First-order and stochastic optimization methods for machine learning
• Concentrated Differential Privacy: Simplifications, Extensions, and Lower Bounds
• The Algorithmic Foundations of Differential Privacy
• Analysis and Design of Optimization Algorithms via Integral Quadratic Constraints
• Differential Privacy: A Survey of Results
• Analysis of Optimization Algorithms via Integral Quadratic Constraints: Nonstrongly Convex Problems
• Robustness of Accelerated First-Order Algorithms for Strongly Convex Optimization Problems
• Variational Bayes In Private Settings (VIPS)
• Adaptive restart of accelerated gradient methods under local quadratic growth condition
• Some methods of speeding up the convergence of iteration methods
• Robust Accelerated Gradient Methods for Smooth Strongly Convex Functions
• Differential Privacy