Graph explorer

Kolmogorov--Arnold stability

Regarding the representation theorem of Kolmogorov and Arnold (KA) as an algorithm for representing or <<expressing>> 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.

6 nodes8 linksoverview previewKolmogorov--Arnold stability
6 nodes8 links
Kolmogorov--Arnold stability6 visible / 6 total nodes / 9 links
Related contextRelated contextRelated contextCo-authorshipAuthorshipAuthorshipTopic signalTopic signalTopic signalWKolmogorov--Arnold stabilitypreprint / 2026ASviatoslav V. DzhenzherResearcherAMichael H. FreedmanResearcherTMachine Learning49008 worksTArtificial Intelligence22915 worksTmath.FA4066 works
PaperSignal 105 links

Kolmogorov--Arnold stability

preprint / 2026

Open