arXiv Machine Learning October 16, 2026 By Yunhao Ni, Yuxin Guo, Jie Luo, Wenjun Wu, Lei Huang

Kolmogorov-Arnold Networks: Curse of Dimensionality and Structural Bias

Read the original on arXiv Machine Learning →

The paper investigates Kolmogorov‑Arnold networks (KANs) and their approximation properties. It shows that while KANs can achieve dimension‑independent approximation exponents for targets with smooth univariate edge functions, this advantage is tied to the target structure rather than the architecture itself. Empirical tests reveal that KANs outperform MLPs only when each nonlinear component depends on a single input coordinate; otherwise, MLPs can be more efficient, especially under tight parameter budgets or for interacting targets.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

safety

arXiv AI

Jul 20

Kolmogorov--Arnold Networks for Small Language Models

arXiv:2607. 15525v1 Announce Type: cross Abstract: Kolmogorov--Arnold Networks (KANs) replace fixed node activations with learned one-dimensional edge functions, offering an explicit interface for interpretation and a possible alternative to transformer feed-forward networks.

By Felippe Alves, Renato Vicente

llms efficiency benchmarks

arXiv Machine Learning

Jul 31

On the Rate of Convergence of Kolmogorov-Arnold Network Regression Estimators

arXiv:2509. 19830v3 Announce Type: replace Abstract: Kolmogorov-Arnold Networks (KANs) approximate multivariate functions by composing univariate transformations through additive or multiplicative aggregation.

By Wei Liu, Eleni Chatzi, Zhilu Lai

Hugging Face Trending Papers

Aug 26

Geometry-Constrained Kolmogorov-Arnold Networks: Learning Edge Geometry via Banach Duality

Kolmogorov-Arnold Networks (KANs) replace fixed activations in deep architectures with learnable univariate edge functions, making the choice of edge parametrisation central. Existing variants rely on...

benchmarks

arXiv AI

Aug 13

Making Gaussian Kolmogorov-Arnold Networks Reliable and Accurate

arXiv:2604. 21174v3 Announce Type: replace-cross Abstract: Kolmogorov-Arnold Networks (KANs) replace fixed activations with learnable univariate edge functions whose behavior depends strongly on the chosen basis.

By Amir Noorizadegan, Sifan Wang, Leevan Ling

arXiv Machine Learning

Oct 3

Neural scaling laws and evolution of learnable activation functions of Kolmogorov-Arnold networks

The paper studies Kolmogorov‑Arnold Networks (KANs), a neural architecture that treats activation functions as learnable components, offering improved interpretability for scientific applications. It investigates how KANs scale with dataset size on image classification tasks (MNIST, Fashion‑MNIST) and a magnetic‑parameter regression task, revealing a broken neural scaling law that transitions from a faster to a slower decay of test loss as data grows. The authors also analyze how the learned activation functions evolve from simple linear approximations to more complex, interpretable symbolic forms as more data is provided.

By Tilen Cadez, Sanghoon Lee, Kyoung-Min Kim

computer-vision benchmarks safety

Hugging Face Trending Papers

Jun 16

Monotonic Kolmogorov-Arnold Networks: A Theoretical and Empirical Study of Monotonicity as an Inductive Bias

Monotonicity has been a long-running architectural inductive bias for neural networks, motivated by tabular, scientific, and economic settings where outputs are known to respond monotonically to certain inputs. Existing approaches are MLP- or flow-based and lack per-edge functional transparency; the only Kolmogorov--Arnold Network (KAN) variant with monotonicity, MonoKAN, enforces the constraint only on a restricted parameter subset and requires a projection-style training procedure.

benchmarks safety