摘要
Stochasticapproximationproblemistofindsomerootorextremumofanon-linearfunctionforwhichonlynoisymeasurementsofthefunctionareavailable.TheclassicalalgorithmforstochasticapproximationproblemistheRobbins-Monro(RM)algorithm,whichusesthenoisyevaluationofthenegativegradientdirectionastheiterativedirection.InordertoacceleratetheRMalgorithm,thispapergivesaflamealgorithmusingadaptiveiterativedirections.Ateachiteration,thenewalgorithmgoestowardseitherthenoisyevaluationofthenegativegradientdirectionorsomeotherdirectionsundersomeswitchcriterions.Twofeasiblechoicesofthecriterionsarepro-posedandtwocorrespondingflamealgorithmsareformed.Differentchoicesofthedirectionsunderthesamegivenswitchcriterionintheflamecanalsoformdifferentalgorithms.Wealsoproposedthesimultanousperturbationdifferenceformsforthetwoflamealgorithms.Thealmostsurelyconvergenceofthenewalgorithmsareallestablished.Thenumericalexperimentsshowthatthenewalgorithmsarepromising.
出版日期
2008年04月14日（中国期刊网平台首次上网日期，不代表论文的发表时间）
