/Local-Approximations-for-SuS

Local Approximations for Subset Simulation method. It is a sequential design (active learning) based on polynomial regression and Gaussian process to quantify extreme events efficiently.

Primary LanguageMATLABOtherNOASSERTION

Local Approximations for Subset Simulation method
---------------------------------------------------------------------------
Created by:
Kenan Šehić (kense@dtu.dk; mrsehickenan@gmail.com)
Department of Applied Mathematics and Computer Science
Technical University of Denmark
Licence: Copyright (C) 2019 Kenan Šehić DTU Compute, Technical University of Denmark

Cite: Šehić K., Karamehmedović M.: Estimation of Failure Probabilities via Local Subset Approximations, TBD
---------------------------------------------------------------------------
Version December 2019
---------------------------------------------------------------------------
* Main Ref:
      
    Subset Simulation Method - Felipe Uribe (felipe.uribe@tum.de)
    https://www.bgu.tum.de/era/software/software00/subset-simulation/
    
    Papaioannou I., Betz W., Zwirglmaier K., Straub D.: MCMC algorithms for subset simulation. Probabilistic Engineering Mechanics, 41: 89-103.

    P. R. Conrad, Y. M. Marzouk,N. S. Pillai and A. Smith: Accelerating Asymptotically Exact MCMC for Computationally Intensive Models via Local Approximations.
    Journal of the American Statistical Association, Volume 111, 2016 - Issue 516, Pages 1591-1607

---------------------------------------------------------------------------

1. You will need to have MATLAB2019B or similar.
2. Download folders to your directory.
3. Select which Gaussian -gp or polynomial regression -poly folder.
4. Open SuS_xxx.m
5. Follow comments
6. Run and explore

If you find any mistake or bug or you have comments, please contact me at kense@dtu.dk or mrsehickenan@gmail.com.

Thank you!