Optimization and learning with randomly compressed gradient updates

DOI10.1162/NECO_A_01588MaRDI QIDQ6982753zbMATH OpenFDO

Authors Zhanliang Huang, Yunwen Lei, Ata Kabán

Publication date 16 May 2025

Published in Neural Computation (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1162/NECO_A_01588

Mathematics Subject Classification ID

Stochastic programming (90C15)

Cites work

• 10.1162/153244302760200704
• A convex formulation for high-dimensional sparse sliced inverse regression
• An elementary proof of a theorem of Johnson and Lindenstrauss
• Convexity, Classification, and Risk Bounds
• Differential Privacy
• Differentially private SGD with non-smooth losses
• Distribution-free performance bounds for potential function rules
• scientific article; zbMATH DE number 6670747 (Why is no real title available?)
• scientific article; zbMATH DE number 4061904 (Why is no real title available?)
• Large-scale distributed sparse class-imbalance learning
• Learnability, stability and uniform convergence
• Optimization methods for large-scale machine learning
• Private empirical risk minimization: efficient algorithms and tight error bounds
• Stability of randomized learning algorithms
• Structured sparsity through convex optimization
• The algorithmic foundations of differential privacy
• Theory of Cryptography

Cited in

(1)

• Select without fear: almost all minibatch schedules generalize optimally

This page was built for publication: Optimization and learning with randomly compressed gradient updates

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6982753)