Kolmogorov--Arnold stability
Abstract
Regarding the representation theorem of Kolmogorov and Arnold (KA) as an algorithm for representing or < > functions, we test its robustness by analyzing its stability to withstand re-parameterizations of the hidden space. One may think of such re-parameterizations as the work of an adversary attempting to foil the construction of the KA outer function. We find KA to be stable under countable collections of continuous re-parameterizations, but unearth a question about the equi-continuity of the outer functions that, so far, obstructs taking limits and defeating continuous groups of re-parameterizations. This question on the regularity of the outer functions is relevant to the debate over the applicability of KA to the general theory of NNs.
Fields of Study & Subjects
Computability
Logic
AI Algorithms
Polynomial and algebraic computation
Markov Chains and Monte Carlo Methods
Publication details
- Journal / source
- Advances in Theoretical and Mathematical Physics
- Publisher
- International Press of Boston
- Volume
- 29
- Issue
- 8
- Pages
- 2285–2303
- Publication date
- 1 January 2026
- Language
- EN