Timezone: »

 
Spotlight
AutoIP: A United Framework to Integrate Physics into Gaussian Processes
Da Long · Zheng Wang · Aditi Krishnapriyan · Robert Kirby · Shandian Zhe · Michael Mahoney

Thu Jul 21 08:45 AM -- 08:50 AM (PDT) @ Room 309
in Miscellaneous Aspects of Machine Learning »

Physical modeling is critical for many modern science and engineering applications. From a data science or machine learning perspective, where more domain-agnostic, data-driven models are pervasive, physical knowledge — often expressed as differential equations — is valuable in that it is complementary to data, and it can potentially help overcome issues such as data sparsity, noise, and inaccuracy. In this work, we propose a simple, yet powerful and general framework — AutoIP, for Automatically Incorporating Physics — that can integrate all kinds of differential equations into Gaussian Processes (GPs) to enhance prediction accuracy and uncertainty quantification. These equations can be linear or nonlinear, spatial, temporal, or spatio-temporal, complete or incomplete with unknown source terms, and so on. Based on kernel differentiation, we construct a GP prior to sample the values of the target function, equation related derivatives, and latent source functions, which are all jointly from a multivariate Gaussian distribution. The sampled values are fed to two likelihoods: one to fit the observations, and the other to conform to the equation. We use the whitening method to evade the strong dependency between the sampled function values and kernel parameters, and we develop a stochastic variational learning algorithm. AutoIP shows improvement upon vanilla GPs in both simulation and several real-world applications, even using rough, incomplete equations.

Keywords: APP: Physics · PM: Bayesian Models and Methods · PM: Gaussian Processes · PM: Graphical Models · PM: Variational Inference

Author Information

Da Long (The University of Utah)
Zheng Wang (University of Utah)
Aditi Krishnapriyan (UC Berkeley)
Robert Kirby (University of Utah)
Shandian Zhe (University of Utah)
Michael Mahoney (UC Berkeley)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors