Multifidelity conditional value-at-risk estimation by dimensionally decomposed generalized polynomial chaos-Kriging

被引:3
|
作者
Lee, Dongjin [1 ]
Kramer, Boris [1 ]
机构
[1] Univ Calif San Diego, Dept Mech & Aerosp Engn, San Diego, CA 92161 USA
关键词
Risk measures; Conditional Value-at-Risk; Dimensionally decomposed generalized; polynomial chaos expansion; Kriging; Importance sampling; Multifidelity importance sampling; UNCERTAINTY QUANTIFICATION; OPTIMIZATION;
D O I
10.1016/j.ress.2023.109208
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
We propose novel methods for Conditional Value-at-Risk (CVaR) estimation for nonlinear systems under high-dimensional dependent random inputs. We develop a novel DD-GPCE-Kriging surrogate that merges dimensionally decomposed generalized polynomial chaos expansion and Kriging to accurately approximate nonlinear and nonsmooth random outputs. We use DD-GPCE-Kriging (1) for Monte Carlo simulation (MCS) and (2) within multifidelity importance sampling (MFIS). The MCS-based method samples from DD-GPCE-Kriging, which is efficient and accurate for high-dimensional dependent random inputs, yet introduces bias. Thus, we propose an MFIS-based method where DD-GPCE-Kriging determines the biasing density, from which we draw a few high-fidelity samples to provide an unbiased CVaR estimate. To accelerate the biasing density construction, we compute DD-GPCE-Kriging using a cheap-to-evaluate low-fidelity model. Numerical results for mathematical functions show that the MFIS-based method is more accurate than the MCS-based method when the output is nonsmooth. The scalability of the proposed methods and their applicability to complex engineering problems are demonstrated on a two-dimensional composite laminate with 28 (partly dependent) random inputs and a three-dimensional composite T-joint with 20 (partly dependent) random inputs. In the former, the proposed MFIS-based method achieves 104x speedup compared to standard MCS using the high-fidelity model, while accurately estimating CVaR with 1.15% error.
引用
收藏
页数:18
相关论文
共 28 条
  • [1] Bi-fidelity conditional value-at-risk estimation by dimensionally decomposed generalized polynomial chaos expansion
    Lee, Dongjin
    Kramer, Boris
    STRUCTURAL AND MULTIDISCIPLINARY OPTIMIZATION, 2023, 66 (02)
  • [2] Bi-fidelity conditional value-at-risk estimation by dimensionally decomposed generalized polynomial chaos expansion
    Dongjin Lee
    Boris Kramer
    Structural and Multidisciplinary Optimization, 2023, 66
  • [3] Conditional Value-at-Risk and Average Value-at-Risk: Estimation and Asymptotics
    Chun, So Yeon
    Shapiro, Alexander
    Uryasev, Stan
    OPERATIONS RESEARCH, 2012, 60 (04) : 739 - 756
  • [4] STOCHASTIC KRIGING FOR CONDITIONAL VALUE-AT-RISK AND ITS SENSITIVITIES
    Chen, Xi
    Nelson, Barry L.
    Kim, Kyoung-Kuk
    2012 WINTER SIMULATION CONFERENCE (WSC), 2012,
  • [5] MONTE CARLO ESTIMATION OF VALUE-AT-RISK, CONDITIONAL VALUE-AT-RISK AND THEIR SENSITIVITIES
    Hong, L. Jeff
    Liu, Guangwu
    PROCEEDINGS OF THE 2011 WINTER SIMULATION CONFERENCE (WSC), 2011, : 95 - 107
  • [6] Rapid Multi-band Patch Antenna Yield Estimation Using Polynomial Chaos-Kriging
    Du, Xiaosong
    Leifsson, Leifur
    Koziel, Slawomir
    COMPUTATIONAL SCIENCE - ICCS 2019, PT III, 2019, 11538 : 487 - 494
  • [7] Conditional Value-at-Risk: Semiparametric estimation and inference
    Wang, Chuan-Sheng
    Zhao, Zhibiao
    JOURNAL OF ECONOMETRICS, 2016, 195 (01) : 86 - 103
  • [8] Robust Conditional Variance and Value-at-Risk Estimation
    Dupuis, Debbie J.
    Papageorgiou, Nicolas
    Remillard, Bruno
    JOURNAL OF FINANCIAL ECONOMETRICS, 2015, 13 (04) : 896 - 921
  • [9] Estimation of Conditional Value-at-Risk in Linear Model
    Jureckova, Jana
    Picek, Jan
    Kalina, Jan
    COMBINING, MODELLING AND ANALYZING IMPRECISION, RANDOMNESS AND DEPENDENCE, SMPS 2024, 2024, 1458 : 200 - 207
  • [10] Conditional value-at-risk: Aspects of modeling and estimation
    Chernozhukov V.
    Umantsev L.
    Empirical Economics, 2001, 26 (1) : 271 - 292