Speeding up rare event simulations using Kriging models

A.K. Tyagi; X. Jonsson; T.G.J. Beelen; W.H.A. Schilders

doi:10.1109/SaPIW.2017.7944001

Speeding up rare event simulations using Kriging models

A.K. Tyagi
, X. Jonsson
, T.G.J. Beelen
, W.H.A. Schilders

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

1 Citation (Scopus)

Abstract

We consider the Importance Sampling Monte Carlo (ISMC) as a reference probability estimator for estimating very small probabilities in the context of analog circuits design. We propose a surrogate based hybrid ISMC method to accelerate the estimation of probabilities when the budget of simulations is limited. The Kriging model is used as a surrogate of the simulator because it provides the uncertainties around the predictions that are useful to obtain confidence bounds for any model predictions, and consequently for the probability estimators.

Original language	English
Title of host publication	2017 IEEE 21st Workshop on Signal and Power Integrity, SPI 2017 - Proceedings
Place of Publication	Piscataway
Publisher	Institute of Electrical and Electronics Engineers
Number of pages	4
ISBN (Electronic)	978-1-5090-5616-3
DOIs	https://doi.org/10.1109/SaPIW.2017.7944001
Publication status	Published - 7 Jun 2017
Event	21th IEEE Workshop on Signal and Power Integrity (SPI 2017), 7-10 May 2017, Lake Maggiore (Baveno), Italy - Lake Maggiore (Baveno), Italy Duration: 7 May 2017 → 10 May 2017 http://www.spi2017.org/home.asp

Workshop

Workshop	21th IEEE Workshop on Signal and Power Integrity (SPI 2017), 7-10 May 2017, Lake Maggiore (Baveno), Italy
Abbreviated title	SPI 2017
Country/Territory	Italy
City	Lake Maggiore (Baveno)
Period	7/05/17 → 10/05/17
Internet address	http://www.spi2017.org/home.asp

Access to Document

10.1109/SaPIW.2017.7944001

Cite this

@inproceedings{701584ab08cc45dc8a30bdd03decbe4b,

title = "Speeding up rare event simulations using Kriging models",

abstract = "We consider the Importance Sampling Monte Carlo (ISMC) as a reference probability estimator for estimating very small probabilities in the context of analog circuits design. We propose a surrogate based hybrid ISMC method to accelerate the estimation of probabilities when the budget of simulations is limited. The Kriging model is used as a surrogate of the simulator because it provides the uncertainties around the predictions that are useful to obtain confidence bounds for any model predictions, and consequently for the probability estimators.",

author = "A.K. Tyagi and X. Jonsson and T.G.J. Beelen and W.H.A. Schilders",

year = "2017",

month = jun,

day = "7",

doi = "10.1109/SaPIW.2017.7944001",

language = "English",

booktitle = "2017 IEEE 21st Workshop on Signal and Power Integrity, SPI 2017 - Proceedings",

publisher = "Institute of Electrical and Electronics Engineers",

address = "United States",

note = "21th IEEE Workshop on Signal and Power Integrity (SPI 2017), 7-10 May 2017, Lake Maggiore (Baveno), Italy, SPI 2017 ; Conference date: 07-05-2017 Through 10-05-2017",

url = "http://www.spi2017.org/home.asp",

}

Tyagi, AK, Jonsson, X, Beelen, TGJ & Schilders, WHA 2017, Speeding up rare event simulations using Kriging models. in 2017 IEEE 21st Workshop on Signal and Power Integrity, SPI 2017 - Proceedings., 7944001, Institute of Electrical and Electronics Engineers, Piscataway, 21th IEEE Workshop on Signal and Power Integrity (SPI 2017), 7-10 May 2017, Lake Maggiore (Baveno), Italy, Lake Maggiore (Baveno), Italy, 7/05/17. https://doi.org/10.1109/SaPIW.2017.7944001

Speeding up rare event simulations using Kriging models. / Tyagi, A.K.; Jonsson, X.; Beelen, T.G.J. et al.
2017 IEEE 21st Workshop on Signal and Power Integrity, SPI 2017 - Proceedings. Piscataway: Institute of Electrical and Electronics Engineers, 2017. 7944001.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Speeding up rare event simulations using Kriging models

AU - Tyagi, A.K.

AU - Jonsson, X.

AU - Beelen, T.G.J.

AU - Schilders, W.H.A.

PY - 2017/6/7

Y1 - 2017/6/7

N2 - We consider the Importance Sampling Monte Carlo (ISMC) as a reference probability estimator for estimating very small probabilities in the context of analog circuits design. We propose a surrogate based hybrid ISMC method to accelerate the estimation of probabilities when the budget of simulations is limited. The Kriging model is used as a surrogate of the simulator because it provides the uncertainties around the predictions that are useful to obtain confidence bounds for any model predictions, and consequently for the probability estimators.

AB - We consider the Importance Sampling Monte Carlo (ISMC) as a reference probability estimator for estimating very small probabilities in the context of analog circuits design. We propose a surrogate based hybrid ISMC method to accelerate the estimation of probabilities when the budget of simulations is limited. The Kriging model is used as a surrogate of the simulator because it provides the uncertainties around the predictions that are useful to obtain confidence bounds for any model predictions, and consequently for the probability estimators.

UR - https://www.scopus.com/pages/publications/85022231043

U2 - 10.1109/SaPIW.2017.7944001

DO - 10.1109/SaPIW.2017.7944001

M3 - Conference contribution

AN - SCOPUS:85022231043

BT - 2017 IEEE 21st Workshop on Signal and Power Integrity, SPI 2017 - Proceedings

PB - Institute of Electrical and Electronics Engineers

CY - Piscataway

T2 - 21th IEEE Workshop on Signal and Power Integrity (SPI 2017), 7-10 May 2017, Lake Maggiore (Baveno), Italy

Y2 - 7 May 2017 through 10 May 2017

ER -

Speeding up rare event simulations using Kriging models

Abstract

Workshop

Access to Document

Other files and links

Fingerprint

Cite this