Two timescale analysis of the Alopex algorithm for optimization

Authors:
P. S. Sastry;M. Magesh;K. P. Unnikrishnan
Affiliations:
Department of Electrical Engineering, Indian Institute of Science, Bangalore 560012, India;Department of Electrical Engineering, Indian Institute of Science, Bangalore 560012, India;General Motors R&D Center, Warren, MI
Venue:
Neural Computation
Year:
2002

Citing 9
Cited 2

Learning automata: an introduction

Learning automata: an introduction
Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning

Machine Learning
On the Handling of Continuous-Valued Attributes in Decision Tree Generation

Machine Learning
A recurrent neural network controller and learning algorithm for the on-line learning control of autonomous underwater vehicles

Neural Networks
Multivariate Decision Trees

Machine Learning
Stochastic approximation with two time scales

Systems & Control Letters
Supervised and unsupervised pattern recognition: feature extraction and computational intelligence

Supervised and unsupervised pattern recognition: feature extraction and computational intelligence
New algorithms for learning and pruning oblique decision trees

IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews
Stochastic optimization over continuous and discrete variables with applications to concept learning under noise

IEEE Transactions on Systems, Man, and Cybernetics, Part A: Systems and Humans

A Novel Model-Based Hearing Compensation Design Using a Gradient-Free Optimization Method

Neural Computation
Annealing stochastic approximation Monte Carlo algorithm for neural network training

Machine Learning

Quantified Score

Hi-index	0.00

Visualization

Abstract

Alopex is a correlation-based gradient-free optimization technique useful in many learning problems. However, there are no analytical results on the asymptotic behavior of this algorithm. This article presents a new version of Alopex that can be analyzed using techniques of two timescale stochastic approximation method. It is shown that the algorithm asymptotically behaves like a gradient-descent method, though it does not need (or estimate) any gradient information. It is also shown, through simulations, that the algorithm is quite effective.