Understanding generalization error of SGD in nonconvex optimization

DOI10.1007/s10994-021-06056-wOpenAlexW3203457432MaRDI QIDQ2127232

Yanyan Li

Publication date: 20 April 2022

Published in: Machine Learning (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s10994-021-06056-w

zbMATH Keywords

stochastic gradient descentgeneralization errornonconvex machine learning

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Uses Software

• LIBSVM
• CIFAR

Cites Work

• A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems
• Robustness and generalization
• Convergence of descent methods for semi-algebraic and tame problems: proximal algorithms, forward-backward splitting, and regularized Gauss-Seidel methods
• Rapid, robust, and reliable blind deconvolution via nonconvex optimization
• Large-Scale Machine Learning with Stochastic Gradient Descent
• Robust Stochastic Approximation Approach to Stochastic Programming
• A theory of the learnable
• Robust Large Margin Deep Neural Networks
• Optimal Rates for Multi-pass Stochastic Gradient Methods
• 10.1162/153244302760200704
• Understanding Machine Learning
• Convex analysis and monotone operator theory in Hilbert spaces
• Mini-batch stochastic approximation methods for nonconvex stochastic composite optimization
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item