Multi-fidelity classification using Gaussian processes: Accelerating the prediction of large-scale computational models
- Pontificia Universidad Católica de Chile, Santiago (Chile). Institute for Biological and Medical Engineering, Schools of Engineering, Medicine and Biological Sciences; Millennium Nucleus for Cardiovascular Magnetic Resonance (Chile)
- Univ. of Pennsylvania, Philadelphia, PA (United States)
- Stanford Univ., CA (United States)
We report that machine learning techniques typically rely on large datasets to create accurate classifiers. However, there are situations when data is scarce and expensive to acquire. This is the case of studies that rely on state-of-the-art computational models which typically take days to run, thus hindering the potential of machine learning tools. In this work, we present a novel classifier that takes advantage of lower fidelity models and inexpensive approximations to predict the binary output of expensive computer simulations. We postulate an autoregressive model between the different levels of fidelity with Gaussian process priors. We adopt a fully Bayesian treatment for the hyper-parameters and use Markov Chain Monte Carlo samplers. We take advantage of the probabilistic nature of the classifier to implement active learning strategies. We also introduce a sparse approximation to enhance the ability of the multi-fidelity classifier to handle a large amount of low fidelity samples. We test these multi-fidelity classifiers against their single-fidelity counterpart with synthetic data, showing a median computational cost reduction of 23% for a target accuracy of 90%. In an application to cardiac electrophysiology, the multi-fidelity classifier achieves an F1 score, the harmonic mean of precision and recall, of 99.6% compared to 74.1% of a single-fidelity classifier when both are trained with 50 samples. In general, our results show that the multi-fidelity classifiers outperform their single-fidelity counterpart in terms of accuracy in all cases. Finally, we envision that this new tool will enable researchers to study classification problems that would otherwise be prohibitively expensive. Source code is available at https://github.com/fsahli/MFclass.
- Research Organization:
- Univ. of Pennsylvania, Philadelphia, PA (United States)
- Sponsoring Organization:
- USDOE Office of Science (SC), Advanced Scientific Computing Research (ASCR)
- Grant/Contract Number:
- SC0019116
- OSTI ID:
- 1595796
- Alternate ID(s):
- OSTI ID: 1564273
- Journal Information:
- Computer Methods in Applied Mechanics and Engineering, Vol. 357, Issue C; Related Information: https://github.com/fsahli/MFclass; ISSN 0045-7825
- Publisher:
- ElsevierCopyright Statement
- Country of Publication:
- United States
- Language:
- English
Web of Science
Multiscale Modeling Meets Machine Learning: What Can We Learn?
|
journal | February 2020 |
Integrating machine learning and multiscale modeling—perspectives, challenges, and opportunities in the biological, biomedical, and behavioral sciences
|
journal | November 2019 |
Multiscale modeling meets machine learning: What can we learn? | preprint | January 2019 |
Integrating Machine Learning and Multiscale Modeling: Perspectives, Challenges, and Opportunities in the Biological, Biomedical, and Behavioral Sciences | text | January 2019 |
Similar Records
Non-autoregressive time-series methods for stable parametric reduced-order models
Physics-Informed Neural Networks for Cardiac Activation Mapping