Derivation of coordinate descent algorithms from optimal control theory

DOI10.1007/s43069-023-00215-6zbMath1519.90177arXiv2309.03990OpenAlexW4362471655MaRDI QIDQ6097432

Isaac Michael Ross

Publication date: 5 June 2023

Published in: SN Operations Research Forum (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2309.03990

zbMATH Keywords

convex optimizationmachine learningcoordinate descentsingular optimal control theorynonsmooth control Lyapunov functions

Mathematics Subject Classification ID

Convex programming (90C25) Numerical methods of relaxation type (49M20)

Cites Work

• Convex analysis and nonlinear optimization. Theory and examples.
• Algorithms for unconstrained optimization problems via control theory
• On the bang-bang control approach via a component-wise line search strategy for unconstrained optimization
• Coordinate descent algorithms
• An optimal control theory for nonlinear optimization
• Efficiency of Coordinate Descent Methods on Huge-Scale Optimization Problems
• Variable Metric Method for Minimization
• Optimization Methods for Large-Scale Machine Learning
• Control Perspectives on Numerical Algorithms and Matrix Problems
• Nonlinear Programming
• Optimal control
• Unnamed Item
• Unnamed Item
• Unnamed Item

This page was built for publication: Derivation of coordinate descent algorithms from optimal control theory