Blending physics with data using an efficient Gaussian process regression with soft inequality and monotonicity constraints
In this work, we propose a new Gaussian process (GP) regression framework that enforces the physical constraints in a probabilistic manner. Specifically, we focus on inequality and monotonicity constraints. This GP model is trained by the quantum-inspired Hamiltonian Monte Carlo (QHMC) algorithm, wh...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-01-01
|
| Series: | Frontiers in Mechanical Engineering |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fmech.2024.1410190/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832590817247625216 |
|---|---|
| author | Didem Kochan Xiu Yang |
| author_facet | Didem Kochan Xiu Yang |
| author_sort | Didem Kochan |
| collection | DOAJ |
| description | In this work, we propose a new Gaussian process (GP) regression framework that enforces the physical constraints in a probabilistic manner. Specifically, we focus on inequality and monotonicity constraints. This GP model is trained by the quantum-inspired Hamiltonian Monte Carlo (QHMC) algorithm, which is an efficient way to sample from a broad class of distributions by allowing a particle to have a random mass matrix with a probability distribution. Integrating the QHMC into the inequality and monotonicity constrained GP regression in the probabilistic sense, our approach enhances the accuracy and reduces the variance in the resulting GP model. Additionally, the probabilistic aspect of the method leads to reduced computational expenses and execution time. Further, we present an adaptive learning algorithm that guides the selection of constraint locations. The accuracy and efficiency of the method are demonstrated in estimating the hyperparameter of high-dimensional GP models under noisy conditions, reconstructing the sparsely observed state of a steady state heat transport problem, and learning a conservative tracer distribution from sparse tracer concentration measurements. |
| format | Article |
| id | doaj-art-687a9df4ebbb4ea495a85158e6155dd4 |
| institution | Kabale University |
| issn | 2297-3079 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Mechanical Engineering |
| spelling | doaj-art-687a9df4ebbb4ea495a85158e6155dd42025-01-23T06:56:37ZengFrontiers Media S.A.Frontiers in Mechanical Engineering2297-30792025-01-011010.3389/fmech.2024.14101901410190Blending physics with data using an efficient Gaussian process regression with soft inequality and monotonicity constraintsDidem KochanXiu YangIn this work, we propose a new Gaussian process (GP) regression framework that enforces the physical constraints in a probabilistic manner. Specifically, we focus on inequality and monotonicity constraints. This GP model is trained by the quantum-inspired Hamiltonian Monte Carlo (QHMC) algorithm, which is an efficient way to sample from a broad class of distributions by allowing a particle to have a random mass matrix with a probability distribution. Integrating the QHMC into the inequality and monotonicity constrained GP regression in the probabilistic sense, our approach enhances the accuracy and reduces the variance in the resulting GP model. Additionally, the probabilistic aspect of the method leads to reduced computational expenses and execution time. Further, we present an adaptive learning algorithm that guides the selection of constraint locations. The accuracy and efficiency of the method are demonstrated in estimating the hyperparameter of high-dimensional GP models under noisy conditions, reconstructing the sparsely observed state of a steady state heat transport problem, and learning a conservative tracer distribution from sparse tracer concentration measurements.https://www.frontiersin.org/articles/10.3389/fmech.2024.1410190/fullconstrained optimizationGaussian process regressionquantum-inspired Hamiltonian Monte Carloadaptive learningsoft constraints |
| spellingShingle | Didem Kochan Xiu Yang Blending physics with data using an efficient Gaussian process regression with soft inequality and monotonicity constraints Frontiers in Mechanical Engineering constrained optimization Gaussian process regression quantum-inspired Hamiltonian Monte Carlo adaptive learning soft constraints |
| title | Blending physics with data using an efficient Gaussian process regression with soft inequality and monotonicity constraints |
| title_full | Blending physics with data using an efficient Gaussian process regression with soft inequality and monotonicity constraints |
| title_fullStr | Blending physics with data using an efficient Gaussian process regression with soft inequality and monotonicity constraints |
| title_full_unstemmed | Blending physics with data using an efficient Gaussian process regression with soft inequality and monotonicity constraints |
| title_short | Blending physics with data using an efficient Gaussian process regression with soft inequality and monotonicity constraints |
| title_sort | blending physics with data using an efficient gaussian process regression with soft inequality and monotonicity constraints |
| topic | constrained optimization Gaussian process regression quantum-inspired Hamiltonian Monte Carlo adaptive learning soft constraints |
| url | https://www.frontiersin.org/articles/10.3389/fmech.2024.1410190/full |
| work_keys_str_mv | AT didemkochan blendingphysicswithdatausinganefficientgaussianprocessregressionwithsoftinequalityandmonotonicityconstraints AT xiuyang blendingphysicswithdatausinganefficientgaussianprocessregressionwithsoftinequalityandmonotonicityconstraints |