A deep learning based surrogate model for stochastic simulators. (April 2022)

• Record Type: Journal Article
• Authors: Thakur, Akshay; Chakraborty, Souvik
• Is Part Of: Probabilistic engineering mechanics. Volume 68(2022)
• Publication Date: 2022-04
• Subjects: Deep learning -- Stochastic simulator -- Uncertainty -- Kernel method; Engineering -- Statistical methods -- Periodicals; Mechanics, Applied -- Statistical methods -- Periodicals; Probabilities -- Periodicals; Ingénierie -- Méthodes statistiques -- Périodiques; Mécanique appliquée -- Méthodes statistiques -- Périodiques; Probabilités -- Périodiques; 620.100727
• DOI: 10.1016/j.probengmech.2022.103248
• Languages: English
• ISSNs: 0266-8920

Abstract

Abstract: We propose a deep learning-based surrogate model for stochastic simulators. The basic idea is to use a generative neural network to approximate the stochastic response. The challenge with such a framework resides in designing the network architecture and selecting loss-function suitable for a stochastic response. While we utilize a simple feed-forward neural network, we propose to use conditional maximum mean discrepancy (CMMD) as the loss function. CMMD exploits the property of reproducing kernel Hilbert space and allows capturing discrepancy between the target and the neural network predicted distributions. The proposed approach is mathematically rigorous, in the sense that it makes no assumptions about the probability density function of the response. The performance of the proposed approach is illustrated using four benchmark problems selected from the literature. Results obtained indicate the excellent performance of the proposed approach.