Sökning: onr:"swepub:oai:DiVA.org:kth-183460" >
Global Convergence ...
Global Convergence of the Heavy-ball Method for Convex Optimization
-
- Ghadimi, Euhanna (författare)
- KTH,Reglerteknik
-
- Feyzmahdavian, Hamid Reza (författare)
- KTH,Reglerteknik
-
- Johansson, Mikael (författare)
- KTH,Reglerteknik
-
(creator_code:org_t)
- IEEE, 2015
- 2015
- Engelska.
-
Ingår i: European Control Conference (ECC15). - : IEEE.
- Relaterad länk:
-
https://urn.kb.se/re...
-
visa fler...
-
https://doi.org/10.1...
-
visa färre...
Abstract
Ämnesord
Stäng
- This paper establishes global convergence and provides global bounds of the rate of convergence for the Heavy-ball method for convex optimization. When the objective function has Lipschitz-continuous gradient, we show that the Cesáro 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. Numerical examples validate our theoretical findings.
Nyckelord
- Optimization
- Convex
- Heavy ball
- Gradient iteration
Publikations- och innehållstyp
- ref (ämneskategori)
- kon (ämneskategori)