Variational Bayesian surrogate modelling with application to robust design optimisation
arXiv:2404.14857 · doi:10.1016/j.cma.2024.117423
Abstract
Surrogate models provide a quick-to-evaluate approximation to complex computational models and are essential for multi-query problems like design optimisation. The inputs of current deterministic computational models are usually high-dimensional and uncertain. We consider Bayesian inference for constructing statistical surrogates with input uncertainties and intrinsic dimensionality reduction. The surrogate is trained by fitting to data obtained from a deterministic computational model. The assumed prior probability density of the surrogate is a Gaussian process. We determine the respective posterior probability density and parameters of the posited statistical model using variational Bayes. The non-Gaussian posterior is approximated by a Gaussian trial density with free variational parameters and the discrepancy between them is measured using the Kullback-Leibler (KL) divergence. We employ the stochastic gradient method to compute the variational parameters and other statistical model parameters by minimising the KL divergence. We demonstrate the accuracy and versatility of the proposed reduced dimension variational Gaussian process (RDVGP) surrogate on illustrative and robust structural optimisation problems where cost functions depend on a weighted sum of the mean and standard deviation of model outputs.
arXiv comment30 pages, 14 figures
References in corpus (15)
- Adam: A Method for Stochastic Optimization
- Auto-Encoding Variational Bayes
- Variational Inference: A Review for Statisticians
- An Introduction to Variational Autoencoders
- GPyTorch: Blackbox Matrix-Matrix Gaussian Process Inference with GPU Acceleration
- Active subspace methods in theory and practice: applications to kriging surfaces
- Gaussian Processes for Big Data
- The statistical finite element method (statFEM) for coherent synthesis of observation data and model predictions
- Fully probabilistic deep models for forward and inverse problems in parametric PDEs
- Bayesian model and dimension reduction for uncertainty propagation: applications in random media
- A probabilistic generative model for semi-supervised training of coarse-grained surrogates and enforcing physical constraints through virtual observables
- Bayesian learning of orthogonal embeddings for multi-fidelity Gaussian Processes
- Variational Bayesian Approximation of Inverse Problems using Sparse Precision Matrices
- Modeling and Optimization with Gaussian Processes in Reduced Eigenbases -- Extended Version
- Sensitivity-enhanced generalized polynomial chaos for efficient uncertainty quantification