Multi-fidelity Hierarchical Neural Processes

06/10/2022
by   Dongxia Wu, et al.
0

Science and engineering fields use computer simulation extensively. These simulations are often run at multiple levels of sophistication to balance accuracy and efficiency. Multi-fidelity surrogate modeling reduces the computational cost by fusing different simulation outputs. Cheap data generated from low-fidelity simulators can be combined with limited high-quality data generated by an expensive high-fidelity simulator. Existing methods based on Gaussian processes rely on strong assumptions of the kernel functions and can hardly scale to high-dimensional settings. We propose Multi-fidelity Hierarchical Neural Processes (MF-HNP), a unified neural latent variable model for multi-fidelity surrogate modeling. MF-HNP inherits the flexibility and scalability of Neural Processes. The latent variables transform the correlations among different fidelity levels from observations to latent space. The predictions across fidelities are conditionally independent given the latent states. It helps alleviate the error propagation issue in existing methods. MF-HNP is flexible enough to handle non-nested high dimensional data at different fidelity levels with varying input and output dimensions. We evaluate MF-HNP on epidemiology and climate modeling tasks, achieving competitive performance in terms of accuracy and uncertainty estimation. In contrast to deep Gaussian Processes with only low-dimensional (< 10) tasks, our method shows great promise for speeding up high-dimensional complex simulations (over 7000 for epidemiology modeling and 45000 for climate modeling).

READ FULL TEXT

page 5

page 7

page 8

research
05/07/2023

Disentangled Multi-Fidelity Deep Bayesian Active Learning

To balance quality and cost, various domain areas of science and enginee...
research
01/15/2019

Conditional deep surrogate models for stochastic, high-dimensional, and multi-fidelity systems

We present a probabilistic deep learning methodology that enables the co...
research
07/01/2022

Infinite-Fidelity Coregionalization for Physical Simulation

Multi-fidelity modeling and learning are important in physical simulatio...
research
12/04/2021

Data Fusion with Latent Map Gaussian Processes

Multi-fidelity modeling and calibration are data fusion tasks that ubiqu...
research
09/22/2017

Hierarchical Kriging for multi-fidelity aero-servo-elastic simulators - Application to extreme loads on wind turbines

In the present work, we consider multi-fidelity surrogate modelling to f...
research
03/04/2021

Finding Efficient Trade-offs in Multi-Fidelity Response Surface Modeling

In the context of optimization approaches to engineering applications, t...
research
04/26/2016

Deep Multi-fidelity Gaussian Processes

We develop a novel multi-fidelity framework that goes far beyond the cla...

Please sign up or login with your details

Forgot password? Click here to reset