.png){kind=icon}
.png){kind=icon}
Return
Gaussian Processes simplify differential equations
.png){kind=icon}
PRE
AI
DOI：10.1016/j.physd.2025.134988.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
In this paper we use Gaussian processes (kernel methods) to learn mappings between trajectories of distinct differential equations. Our goal is to simplify both the representation and the solution of these equations. We begin by examining the Cole–Hopf transformation, a classical result that converts the nonlinear, viscous Burgers’ equation into the linear heat equation. We demonstrate that this transformation can be effectively learned using Gaussian process regression, either from single or from multiple initial conditions of the Burgers equation. We then extend our methodology to discover mappings between initial conditions of a nonlinear partial differential equation (PDE) and a linear PDE, where the exact form of the linear PDE remains unknown and is inferred through Computational Graph Completion (CGC), a generalization of Gaussian Process Regression from approximating single input/output functions to approximating multiple input/output functions that interact within a computational graph. Further, we employ CGC to identify a local transformation from the nonlinear ordinary differential equation (ODE) of the Brusselator to its Poincaré normal form, capturing the dynamics around a Hopf bifurcation. Moreover, we interpret our learning procedure through Algorithmic Information Theory (AIT) and the Minimal Description Length (MDL) principle, framing these transformations as efficient, succinct encodings that compress nonlinear dynamics into simpler, linearized representations. This MDL perspective not only provides a theoretical justification for kernel-based regression methods but also illuminates the relationship between kernel learning and principles of model simplicity and data compression showing that learning in a reproducing kernel Hilbert space (RKHS) simultaneously minimizes a proxy for Kolmogorov complexity and maximizes algorithmic mutual information between the data and transformation. We conclude by addressing the broader question of whether systematic transformations between nonlinear and linear PDEs can generally exist, suggesting avenues for future research.
Journal
P
IF:
0
Papers:
184
Citations:
0