Global convergence in learning fully-connected ReLU networks via un-rectifying based on the augmented Lagrangian approach

DOI10.1007/s10915-024-02548-8zbMATH Open1546.90213MaRDI QIDQ6536825

Ming-Yu Chung, Shih-Shuo Tung, Jinn Ho, Wen-Liang Hwang

Publication date: 14 May 2024

Published in: Journal of Scientific Computing (Search for Journal in Brave)

zbMATH Keywords

optimizationmachine learningun-rectification

Mathematics Subject Classification ID

Combinatorial optimization (90C27)

Cites Work

• Unnamed Item
• Unnamed Item
• On gradients of functions definable in o-minimal structures
• On semi- and subanalytic geometry
• A globally convergent algorithm for nonconvex optimization based on block coordinate update
• Global convergence of ADMM in nonconvex nonsmooth optimization
• Convergence of descent methods for semi-algebraic and tame problems: proximal algorithms, forward-backward splitting, and regularized Gauss-Seidel methods
• A proposal on machine learning via dynamical systems
• A Globally Convergent Augmented Lagrangian Algorithm for Optimization with General Constraints and Simple Bounds
• Optimization Methods for Large-Scale Machine Learning
• Un-Rectifying Non-Linear Networks for Signal Representation
• ADMM for multiaffine constrained optimization
• Learning representations by back-propagating errors
• On the Convergence of Alternating Direction Lagrangian Methods for Nonconvex Structured Optimization Problems
• A Stochastic Approximation Method

This page was built for publication: Global convergence in learning fully-connected ReLU networks via un-rectifying based on the augmented Lagrangian approach