TY - JOUR
TI - Sufficient conditions for the convergence of nonautonomous stochastic search for a global minimum
AU - Tarłowski, Dawid
TI - Sufficient conditions for the convergence of nonautonomous stochastic search for a global minimum
AB - 
	The majority of stochastic optimization algorithms can be written in the general form xt+1 = Tt(xt; yt), where xt is a sequence of points and parameters which are transformed by the algorithm, Tt are the methods of the algorithm and yt represent the randomness of the algorithm. We extend the results of papers [11] and [14] to provide some new general conditions under which the algorithm finds a global minimum with probability one.
VL - 2011
IS - Tom 49
PY - 2012
SN - 0083-4386
C1 - 2084-3828
SP - 73
EP - 83
DO - 10.4467/20843828AM.12.005.0457
UR - https://ejournals.eu/czasopismo/universitatis-iagellonicae-acta-mathematica/artykul/sufficient-conditions-for-the-convergence-of-nonautonomous-stochastic-search-for-a-global-minimum
KW - Stochastic optimization
KW - global optimization
KW - Lyapunov function
KW - weak convergence of measures