Revisiting Normalized Gradient Descent: Fast Evasion of Saddle Points

DOI10.1109/TAC.2019.2914998zbMath1482.90174arXiv1711.05224OpenAlexW2963886613WikidataQ127814923 ScholiaQ127814923MaRDI QIDQ5211250

Brian Swenson, Soummya Kar, Ryan W. Murray

Publication date: 28 January 2020

Published in: IEEE Transactions on Automatic Control (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1711.05224

Mathematics Subject Classification ID

Nonconvex programming, global optimization (90C26) Numerical optimization and variational techniques (65K10) Asymptotic properties of solutions to ordinary differential equations (34D05)

Related Items (4)

Robust preconditioned one-shot methods and direct-adjoint-looping for optimizing Reynolds-averaged turbulent flows ⋮ Gradient descent with random initialization: fast global convergence for nonconvex phase retrieval ⋮ A universal quantum algorithm for weighted maximum cut and Ising problems ⋮ Unnamed Item

This page was built for publication: Revisiting Normalized Gradient Descent: Fast Evasion of Saddle Points