Deeply uncertain: comparing methods of uncertainty quantification in deep learning algorithms
We present a comparison of methods for uncertainty quantification (UQ) in deep learning algorithms in the context of a simple physical system. Three of the most common uncertainty quantification methods - Bayesian Neural Networks (BNN), Concrete Dropout (CD), and Deep Ensembles (DE) - are compared to the standard analytic error propagation. We discuss this comparison in terms endemic to both machine learning ("epistemic" and "aleatoric") and the physical sciences ("statistical" and "systematic"). The comparisons are presented in terms of simulated experimental measurements of a single pendulum - a prototypical physical system for studying measurement and analysis techniques. Our results highlight some pitfalls that may occur when using these UQ methods. For example, when the variation of noise in the training set is small, all methods predicted the same relative uncertainty independently of the inputs. This issue is particularly hard to avoid in BNN. On the other hand, when the test set contains samples far from the training distribution, we found that no methods sufficiently increased the uncertainties associated to their predictions. This problem was particularly clear for CD. In light of these results, we make some recommendations for usage and interpretation of UQ methods.
- Research Organization:
- Fermi National Accelerator Laboratory (FNAL), Batavia, IL (United States)
- Sponsoring Organization:
- USDOE Office of Science (SC), High Energy Physics (HEP)
- Grant/Contract Number:
- AC02-07CH11359
- OSTI ID:
- 1731011
- Alternate ID(s):
- OSTI ID: 1674984; OSTI ID: 1731012
- Report Number(s):
- arXiv:2004.10710; FERMILAB-PUB-20-157-SCD
- Journal Information:
- Machine Learning: Science and Technology, Journal Name: Machine Learning: Science and Technology Vol. 2 Journal Issue: 1; ISSN 2632-2153
- Publisher:
- IOP PublishingCopyright Statement
- Country of Publication:
- United Kingdom
- Language:
- English
A Hybrid Deep Learning Approach to Cosmological Constraints from Galaxy Redshift Surveys
|
journal | February 2020 |
A high-bias, low-variance introduction to Machine Learning for physicists
|
journal | May 2019 |
Similar Records
Fuel performance uncertainty quantification and sensitivity analysis in the presence of epistemic and aleatoric sources of uncertainties
Prediction of the SYM-H Index Using a Bayesian Deep Learning Method With Uncertainty Quantification