Two Timescale Analysis of the Alopex Algorithm for Optimization

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.

[1]  Evangelia Micheli-Tzanakou,et al.  Supervised and unsupervised pattern recognition: feature extraction and computational intelligence , 2000 .

[2]  Usama M. Fayyad,et al.  On the Handling of Continuous-Valued Attributes in Decision Tree Generation , 1992, Machine Learning.

[3]  Vivek S. Borkar,et al.  Stochastic approximation algorithms: Overview and recent trends , 1999 .

[4]  Alejandro Bia.  Alopex-B: A New, Simpler, But Yet Faster Version Of The Alopex Training Algorithm , 2001, Int. J. Neural Syst..

[5]  Thomas Kailath,et al.  Model-free distributed learning , 1990, IEEE Trans. Neural Networks.

[6]  E Harth,et al.  Alopex: a stochastic method for determining visual receptive fields. , 1974, Vision research.

[7]  Kumpati S. Narendra,et al.  Learning automata - an introduction , 1989 .

[8]  K. Schittkowski,et al.  NONLINEAR PROGRAMMING , 2022 .

[9]  Simon Kasif,et al.  A System for Induction of Oblique Decision Trees , 1994, J. Artif. Intell. Res..

[10]  E. Harth,et al.  Brainstem control of sensory information: a mechanism for perception. , 1985, International journal of psychophysiology : official journal of the International Organization of Psychophysiology.

[11]  Abhijit S. Pandya,et al.  A recurrent neural network controller and learning algorithm for the on-line learning control of autonomous underwater vehicles , 1994, Neural Networks.

[12]  J. Spall.  Multivariate stochastic approximation using a simultaneous perturbation gradient approximation , 1992 .

[13]  Carlos S. Kubrusly,et al.  Stochastic approximation algorithms and applications , 1973, CDC 1973.

[14]  Marwan A. Jabri,et al.  Weight Perturbation: An Optimal Architecture and Learning Technique for Analog VLSI Feedforward and Recurrent Multilayer Networks , 1991, Neural Comput..

[15]  P. Shanti Sastry,et al.  New algorithms for learning and pruning oblique decision trees , 1999, IEEE Trans. Syst. Man Cybern. Part C.

[16]  P. S. Sastry,et al.  Continuous action set learning automata for stochastic optimization , 1994 .

[17]  Ronald J. Williams,et al.  Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning , 2004, Machine Learning.

[18]  P. Sawchenko,et al.  Localization, secretion, and action of inhibin in human placenta. , 1987, Science.

[19]  Karl Branting,et al.  A computational model of ratio decidendi , 2004, Artificial Intelligence and Law.

[20]  H. S. Nine,et al.  The Role of Subplate Feedback in the Development of Ocular Dominance Columns , 1993 .

[21]  K. P. Unnikrishnan,et al.  Alopex: A Correlation-Based Learning Algorithm for Feedforward and Recurrent Neural Networks , 1994, Neural Computation.

[22]  K. Rajaraman,et al.  Stochastic optimization over continuous and discrete variables with applications to concept learning under noise , 1999, IEEE Trans. Syst. Man Cybern. Part A.

[23]  J. Ross Quinlan,et al.  Learning Efficient Classification Procedures and Their Application to Chess End Games , 1983 .

[24]  Marwan A. Jabri,et al.  Weight Perturbation: An Optimal Architecture and Learning Technique for Analog VLSI Feedforward and Recurrent Multilayer Networks , 1991, Neural Computation.

[25]  V. Borkar.  Stochastic approximation with two time scales , 1997 .

[26]  Abhijit S. Pandya,et al.  Invariant recognition of 2-D objects using Alopex neural networks , 1992, Defense, Security, and Sensing.

[27]  E Harth,et al.  The inversion of sensory processing by feedback pathways: a model of visual cognitive functions. , 1987, Science.

[28]  Carla E. Brodley,et al.  Multivariate decision trees , 2004, Machine Learning.