Convergence Rates of Digital Diffusion Network Algorithms for Global Optimization with Applications to Image Estimation

Authors:
G. Yin;P. A. Kelly
Affiliations:
Department of Mathematics, Wayne State University, Detroit, MI 48202, USA (E-mail: gyin@math.wayne.edu);Department of Electrical & Computer Engineering, University of Massachusetts, Amherst, MA 10013, USA (E-mail: kelly@ecs.umass.edu)
Venue:
Journal of Global Optimization
Year:
2002

Citing 8
Cited 0

Diffusion for global optimization in Rn

SIAM Journal on Control and Optimization
Asymptotic global behavior for stochastic approximation and diffusions with slowly decreasing noise effects: Global minimization via Monte Carlo

SIAM Journal on Applied Mathematics
Recursive stochastic algorithms for global optimization in Rd

SIAM Journal on Control and Optimization
Approximation of an analog diffusion network with applications to image estimation

Journal of Optimization Theory and Applications
Budget-Dependent Convergence Rate of Stochastic Approximation

SIAM Journal on Optimization
Rates of Convergence for a Class of Global Stochastic Optimization Algorithms

SIAM Journal on Optimization
Digital diffusion network for image segmentation

ICIP '95 Proceedings of the 1995 International Conference on Image Processing (Vol. 3)-Volume 3 - Volume 3
Analog optimization with Wong's stochastic neural network

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

Motivated by the recent developments in digital diffusion networks, this work is devoted to the rates of convergence issue for a class of global optimization algorithms. By means of weak convergence methods, we show that a sequence of suitably scaled estimation errors converges weakly to a diffusion process (a solution of a stochastic differential equation). The scaling together with the stationary covariance of the limit diffusion process gives the desired rates of convergence. Application examples are also provided for some image estimation problems.