scholarly journals Global convergence rate of incremental aggregated gradient methods for nonsmooth problems

2016 ◽  
Author(s):  
N. Denizcan Vanli ◽  
Mert Gurbuzbalaban ◽  
Asuman Ozdaglar
Keyword(s):  
Global Convergence ◽  
Convergence Rate ◽  
Gradient Methods ◽  
Nonsmooth Problems ◽  
Global Convergence Rate

scholarly journals Global Convergence Rate of Proximal Incremental Aggregated Gradient Methods

2018 ◽  
Vol 28 (2) ◽  
pp. 1282-1300 ◽  
Author(s):  
N. D. Vanli ◽  
M. Gürbüzbalaban ◽  
A. Ozdaglar
Keyword(s):  
Global Convergence ◽  
Convergence Rate ◽  
Gradient Methods ◽  
Global Convergence Rate

scholarly journals On global convergence rate of two acceleration projection algorithms for solving the multiple-sets split feasibility problem

Filomat ◽  
2016 ◽  
Vol 30 (12) ◽  
pp. 3243-3252 ◽  
Author(s):  
Qiao-Li Dong ◽  
Songnian He ◽  
Yanmin Zhao
Keyword(s):  
Global Convergence ◽  
Convergence Rate ◽  
Numerical Experiments ◽  
Split Feasibility Problem ◽  
Feasibility Problem ◽  
Projection Algorithms ◽  
Split Feasibility ◽  
Global Convergence Rate

In this paper, we introduce two fast projection algorithms for solving the multiple-sets split feasibility problem (MSFP). Our algorithms accelerate algorithms proposed in [8] and are proved to have a global convergence rate O(1=n2). Preliminary numerical experiments show that these algorithms are practical and promising.

Convergence rate of some hybrid multigrid methods for variational inequalities

2015 ◽  
Vol 23 (3) ◽  
Author(s):  
Lori Badea
Keyword(s):  
Global Convergence ◽  
Sobolev Space ◽  
Convergence Rate ◽  
Variational Inequalities ◽  
General Framework ◽  
Multigrid Method ◽  
Multigrid Methods ◽  
Numer Anal ◽  
Global Convergence Rate

AbstractIn [L. Badea, Global convergence rate of a standard multigrid method for variational inequalities, IMA J. Numer. Anal., 34 (2014), No. 1, 197-216], a global convergence rate of the standard monotone multigrid method for variational inequalities is derived. This algorithm can be also viewed as performing multiplicative iterations on each level and also multiplicative iterations over the levels. In the present paper, this algorithm together with other three algorithms,which are combinations of additive or multiplicative iterations on levels with additive or multiplicative iterations over the levels, are analyzed in a unitary manner and in a more general framework which allow us to consider problems in the Sobolev space W

Global Convergence Rate of Recurrently Connected Neural Networks

2002 ◽  
Vol 14 (12) ◽  
pp. 2947-2957 ◽  
Author(s):  
Tianping Chen ◽  
Wenlian Lu ◽  
Shun-ichi Amari
Keyword(s):  
Neural Networks ◽  
Global Convergence ◽  
Convergence Rate ◽  
Exponential Stability ◽  
Recurrent Neural Networks ◽  
Global Exponential Stability ◽  
Sufficient Conditions ◽  
Global Convergence Rate

We discuss recurrently connected neural networks, investigating their global exponential stability (GES). Some sufficient conditions for a class of recurrent neural networks belonging to GES are given. Sharp convergence rate is given too.

Sign in / Sign up

Export Citation Format

Share Document