Variable decoupling and the Kolmogorov Superposition Theorem for rational functions
math.NA, cs.NA
Submitted: 2026-05-08
Updated: 2026-11-10
Code: https://github.com/KindXiaoming/pykan
Project page: https://jonasactor.github.io/files/Papers/Thesis_JonasActor_ConstructiveKST_Final.pdf
Terminology
Sources
- Tensor-based multivariate function approximation: methods benchmarking and comparison
- The Kolmogorov Superposition Theorem can Break the Curse of Dimensionality When Approximating High Dimensional Functions
- KAN: Kolmogorov-Arnold Networks
Related papers
- Do physics-informed neural networks (PINNs) need to be deep? Shallow PINNs using the Levenberg-Marquardt algorithm
- A Neural-preconditioned Poisson Solver for Mixed Dirichlet and Neumann Boundary Conditions
- Advanced Linear Algebra with Applications - Part I (Numerical linear algebra for PDEs, machine learning, and data assimilation)
- Operator learning meets inverse problems: A probabilistic perspective
- Second-order consistency for learning chaotic dynamics via randomized Jacobian matching
- Windowed thinning and query complexity for the bouncy particle and Zigzag samplers