-

 

 

 




Optimization Online





 

Global convergence of the Heavy-ball method for convex optimization

Euhanna Ghadimi(euhanna***at***kth.se)
Hamid Reza Feyzmahdavian(hamidrez***at***kth.se)
Mikael Johansson(mikaelj***at***kth.se)

Abstract: This paper establishes global convergence and provides global bounds of the convergence rate of the Heavy-ball method for convex optimization problems. When the objective function has Lipschitz-continuous gradient, we show that the Cesa ́ro average of the iterates converges to the optimum at a rate of $O(1/k)$ where k is the number of iterations. When the objective function is also strongly convex, we prove that the Heavy-ball iterates converge linearly to the unique optimum.

Keywords: Performance of first-order algorithms, Rate of convergence, Complexity, Smooth convex optimization, Heavy-ball method, Gradient Descent

Category 1: Convex and Nonsmooth Optimization (Convex Optimization )

Category 2: Nonlinear Optimization (Unconstrained Optimization )

Citation:

Download: [PDF]

Entry Submitted: 12/23/2014
Entry Accepted: 12/23/2014
Entry Last Modified: 12/23/2014

Modify/Update this entry


  Visitors Authors More about us Links
  Subscribe, Unsubscribe
Digest Archive
Search, Browse the Repository

 

Submit
Update
Policies
Coordinator's Board
Classification Scheme
Credits
Give us feedback
Optimization Journals, Sites, Societies
Mathematical Optimization Society