mlsanityData to 7 Oct 2026

PAGP: A physics-assisted Gaussian process framework with active learning for forward and inverse problems of partial differential equations

arXiv 2204.02583 ↗First posted 6 Apr 2022stat.ML cs.LG cs.NAcited by 3

Not on the map. Why?

Abstract (arXiv)

In this work, a Gaussian process regression(GPR) model incorporated with given physical information in partial differential equations(PDEs) is developed: physics-assisted Gaussian processes(PAGP). The targets of this model can be divided into two types of problem: finding solutions or discovering unknown coefficients of given PDEs with initial and boundary conditions. We introduce three different models: continuous time, discrete time and hybrid models. The given physical information is integrated into Gaussian process model through our designed GP loss functions. Three types of loss function are provided in this paper based on two different approaches to train the standard GP model. The first part of the paper introduces the continuous time model which treats temporal domain the same as spatial domain. The unknown coefficients in given PDEs can be jointly learned with GP hyper-parameters by minimizing the designed loss function. In the discrete time models, we first choose a time discretization scheme to discretize the temporal domain. Then the PAGP model is applied at each time step together with the scheme to approximate PDE solutions at given test points of final time. To discover unknown coefficients in this setting, observations at two specific time are needed and a mixed mean square error function is constructed to obtain the optimal coefficients. In the last part, a novel hybrid model combining the continuous and discrete time models is presented. It merges the flexibility of continuous time model and the accuracy of the discrete time model. The performance of choosing different models with different GP loss functions is also discussed. The effectiveness of the proposed PAGP methods is illustrated in our numerical section.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 22 of its 66 references that are in the map. First posted on arXiv 6 Apr 2022.

Builds on

22 of 66 references.

References · 22

  1. 2020When and why PINNs fail to train: A neural tangent kernel perspectivecited by 629
  2. 2013Gaussian Processes for Big Datacited by 377
  3. 2019Physics-Constrained Deep Learning for High-dimensional Surrogate Modeling and Uncertainty Quantification without Labeled Datacited by 261
  4. 2020hp-VPINNs: Variational Physics-Informed Neural Networks With Domain Decompositioncited by 236
  5. 2017Hidden Physics Models: Machine Learning of Nonlinear Partial Differential Equationscited by 208
  6. 2018Survey of multifidelity methods in uncertainty propagation, inference, and optimizationcited by 141
  7. 2017Machine Learning of Linear Differential Equations using Gaussian Processescited by 139
  8. 2017Numerical Gaussian Processes for Time-dependent and Non-linear Partial Differential Equationscited by 72
  9. 2015Probabilistic Numerics and Uncertainty in Computationscited by 59
  10. 2016Inferring solutions of differential equations using noisy multi-fidelity datacited by 38
  11. 2018Scaling Gaussian Process Regression with Derivativescited by 27
  12. 2020Macroscopic Traffic Flow Modeling with Physics Regularized Gaussian Process: A New Insight into Machine Learning Applicationscited by 25
10 more
  1. 2014Probabilistic ODE Solvers with Runge-Kutta Meanscited by 22
  2. 2018Neural-net-induced Gaussian process regression for function approximation and PDE solutioncited by 22
  3. 2018Physics-Informed CoKriging: A Gaussian-Process-Regression-Based Multifidelity Method for Data-Model Convergencecited by 16
  4. 2020Gaussian Process Regression constrained by Boundary Value Problemscited by 15
  5. 2019Gaussian Process Assisted Active Learning of Physical Lawscited by 14
  6. 2020Multi-fidelity machine-learning with uncertainty quantification and Bayesian optimization for materials design: Application to ternary random alloyscited by 14
  7. 2021Gaussian processes meet NeuralODEs: A Bayesian framework for learning the dynamics of partially observed systems from scarce and noisy datacited by 13
  8. 2020APIK: Active Physics-Informed Kriging Model with Partial Differential Equationscited by 9
  9. 2020Modeling Stochastic Microscopic Traffic Behaviors: a Physics Regularized Gaussian Process Approachcited by 4
  10. 2020Clustered active-subspace based local Gaussian Process emulator for high-dimensional and complex computer modelscited by 3

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 1; 2024: 1.

3 papers.

  1. 2024Operator Learning with Gaussian Processescited by 18
  2. 2022Gaussian Process Priors for Systems of Linear Partial Differential Equations with Constant Coefficientscited by 17
  3. 2023Random Grid Neural Processes for Parametric Partial Differential Equationscited by 8