On the convergence of the continuous gradient projection method

2018/08/23 by May, Ramzi · 1 citation
#34K25 #49J15 #49M37 #65K10 #FOS: Mathematics #Optimization and Control (math.OC)

paper · doi:10.48550/arxiv.1808.07705

Abstract

We prove the weak and the strong convergence of the trajectories of the continuous gradient projection method under some mild assumptions on the objective function and the step size function. Moreover, we estimate the decay rate to equilibrium when the objective function satisfies a global Holderian error bound inequality.

Cited by

• Inexact projected preconditioned gradient methods with variable metrics: a Lyapunov convergence theory (extended version)

Related

• Continuous-time Lower Bounds for Gradient-based Algorithms
• General Holder Smooth Convergence Rates Follow From Specialized Rates Assuming Growth Bounds
• On the linear convergence of the stochastic gradient method with constant step-size
• Convergence of gradient descent-ascent analyzed as a Newtonian dynamical system with dissipation
• Convergence Rate of Frank-Wolfe for Non-Convex Objectives