It is well-known that the Monte Carlo method is very successful in tackling several kinds of system simulations. It often happens that one has to deal with rare events, and the use of a variance reduction technique is almost mandatory. in order to have Monte Carlo efficient applications. The main issue associated with variance reduction techniques is related to the choice of the value. of the biasing parameter. Actually, this task is typically left to the experience of the Monte Carlo user. who has to make many attempts before achieving an advantageous biasing. A valuable result is provided: a methodology and a practical rule addressed to establish an a priori guidance for the choice of the optimal value of the biasing parameter. This result, which has been obtained for a single component system. has the notable property of being valid for any multicomponent system. In particular, in this paper, the exponential and the uniform biases of exponentially distributed phenomena are investigated thoroughly.

Biased Monte Carlo optimization: the basic approach

SCARDOVELLI, RUBEN;VESTRUCCI, PAOLO
2005

Abstract

It is well-known that the Monte Carlo method is very successful in tackling several kinds of system simulations. It often happens that one has to deal with rare events, and the use of a variance reduction technique is almost mandatory. in order to have Monte Carlo efficient applications. The main issue associated with variance reduction techniques is related to the choice of the value. of the biasing parameter. Actually, this task is typically left to the experience of the Monte Carlo user. who has to make many attempts before achieving an advantageous biasing. A valuable result is provided: a methodology and a practical rule addressed to establish an a priori guidance for the choice of the optimal value of the biasing parameter. This result, which has been obtained for a single component system. has the notable property of being valid for any multicomponent system. In particular, in this paper, the exponential and the uniform biases of exponentially distributed phenomena are investigated thoroughly.
2005
CAMPIONI L.; SCARDOVELLI R.; VESTRUCCI P.
File in questo prodotto:
Eventuali allegati, non sono esposti

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11585/18685
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 7
  • ???jsp.display-item.citation.isi??? 3
social impact