- Tytuł:
- Sufficient conditions for the convergence of nonautonomous stochastic search for a global minimum
- Autorzy:
- Tarłowski, Dawid
- Powiązania:
- https://bibliotekanauki.pl/articles/1368138.pdf
- Data publikacji:
- 2011
- Wydawca:
- Uniwersytet Jagielloński. Wydawnictwo Uniwersytetu Jagiellońskiego
- Opis:
- The majority of stochastic optimization algorithms can be written in the general form $x_{t+1}$ = $T_t$ ($x_t$ ; $y_t$), where xt is a sequence of points and parameters which are transformed by the algorithm, Tt are the methods of the algorithm and $y_t$ 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 nds a global minimum with probability one.
- Źródło:
-
Universitatis Iagellonicae Acta Mathematica; 2011, 49; 73-83
2084-3828
0083-4386 - Pojawia się w:
- Universitatis Iagellonicae Acta Mathematica
- Dostawca treści:
- Biblioteka Nauki
Artykuł