Data-Efficient Kernel Methods for Learning Differential Equations and Their Solution Operators: Algorithms and Error Analysis
stat.ML, cs.LG, cs.NA, math.NA
Submitted: 2025-03-02
Updated: 2026-11-02
Code: https://github.com/TADSGroup/kernelequationlearnin
Terminology
Sources
- Gaussian Processes and Kernel Methods: A Review on Connections and Equivalences
- A Tutorial on Sparse Gaussian Processes and Variational Inference
- Convergence rates of non-stationary and deep Gaussian process regression
- Deep Generative Modeling for Identification of Noisy, Non-Stationary Dynamical Systems
- Operator learning for hyperbolic partial differential equations
- The Stochastic Occupation Kernel Method for System Identification
Related papers
- Uniform-in-Time Weak Propagation-of-Chaos in Shallow Neural Networks
- Diffusion Models Observe Only Gradients: A Geometric Perspective on Score Matching Errors
- Quantifying Error Propagation and Model Collapse in Diffusion Models
- Behavior of prediction performance metrics with rare events
- Statistical Inference and Learning for Shapley Additive Explanations (SHAP)
- Control Variate Design for Score-Function Gradient Estimators in Importance-Weighted Variational Inference