Thumbnail
Access Restriction
Open

Author Yin, G. ♦ G. Rudolph, Y.
Source CiteSeerX
Content type Text
File Format PDF
Subject Domain (in DDC) Computer science, information & general works ♦ Data processing & computer science
Subject Keyword Evolutionary Algorithm ♦ Stochastic Approximation ♦ Weak Sense ♦ Recursive Stochastic Procedure ♦ Evolutionary Computation Algorithm ♦ General Form ♦ Depth Understanding ♦ Step Size Algorithm ♦ Ordinary Di Erential Equation ♦ Stochastic Di Erential Equation ♦ Evolutionary Computation ♦ Natural Connection ♦ Su Cient Condition ♦ Evolution Strategy ♦ Continuous Dynamic ♦ Abbreviated Title ♦ New Domain ♦ Discrete Iteration ♦ Rst Attempt ♦ Stochastic Approximation Procedure ♦ Key Word ♦ Underlying Algorithm ♦ Constant Gain
Abstract This work is our rst attempt in establishing the connections between evolutionary computation algorithms and stochastic approximation procedures. By treating evolutionary algorithms as recursive stochastic procedures, we study both constant gain and decreasing step size algorithms. We formulate the problem in a rather general form, supply the su cient conditions for convergence (both with probability one, and in the weak sense). Among other things, our approach reveals the natural connection of the discrete iterations and the continuous dynamics (ordinary di erential equations, and/or stochastic di erential equations). We hope that this attempt will open up a new domain for further research and lead to in depth understanding of the underlying algorithms. Key words: evolutionary computation, evolution strategy, stochastic approximation, convergence, rate of convergence. Abbreviated title. Connections of EA and SA
Educational Role Student ♦ Teacher
Age Range above 22 year
Educational Use Research
Education Level UG and PG ♦ Career/Technical Study
Publisher Date 1994-01-01