paper-with-me

홈 › Papers

Layer-wise Lipschitz-Product Control for Deep Kolmogorov--Arnold Network Representations of Compositionally Structured Functions

2026-04-29 · Aleksander Tankman arxiv

We prove that any continuous function f from [0,1]^n to R representable by a finite computation tree with N internal nodes and compositional sparsity s = O(1) admits a deep Kolmogorov-Arnold Network (KAN) representation. Each internal node is realised by a primitive KAN block with controlled block depth and Lipschitz product. The layer-wise Lipschitz product satisfies the primary domain-sensitive bound independent of the input dimension n. It simplifies to P(KAN_f) <= max(C*,1)^L_f with L_f <= c_max * N. For the standard operations {+,-,x,sin,cos} with x nodes on [0,1]-bounded inputs we obtain P(KAN) <= 1. Layer widths satisfy n_l <= n + 2 w_max * N. The uniform approximation error is bounded by N * max(C*,1)^d(f) * epsilon_Op (simplifies when C* <=1). For f in C^m we obtain optimal B-spline rates. Range bounds are also derived (B_f <= N+1 for additive trees). This addresses the gap on Lipschitz control in deep KAN stacks noted by Liu et al. (2024). Experiments confirm P(KAN)=1.0 for several compositionally structured functions.

📄 PDF Abstract BibTeX arXiv:2604.26444

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Efficient proximal mapping of the path-norm regularizer of shallow networks

2020-01-01 · ICML 2020 1 · Fabian Latorre, Paul Rolland, Shaul Nadav Hallak, Volkan Cevher

We demonstrate two new important properties of the path-norm regularizer for shallow neural networks. First, despite its non-smoothness and non-convexity it allows a closed form proximal operator which can be efficiently…

Efficient Proximal Mapping of the 1-path-norm of Shallow Networks

2020-07-02 · Fabian Latorre, Paul Rolland, Nadav Hallak, Volkan Cevher

We demonstrate two new important properties of the 1-path-norm of shallow neural networks. First, despite its non-smoothness and non-convexity it allows a closed form proximal operator which can be efficiently computed, …

Kolmogorov Width Decay and Poor Approximators in Machine Learning: Shallow Neural Networks, Random Feature Models and Neural Tangent Kernels

2020-05-21 · Weinan E, Stephan Wojtowytsch

We establish a scale separation of Kolmogorov width type between subspaces of a given Banach space under the condition that a sequence of linear maps converges much faster on one of the subspaces. The general technique i…

Variational Kolmogorov-Arnold Network

2025-07-03 · Francesco Alesiani, Henrik Christiansen, Federico Errica arxiv

Kolmogorov-Arnold Networks (KANs) offer a theoretically grounded alternative to multi-layer perceptrons by representing multivariate functions as compositions of univariate basis functions. However, a critical limitation…

Provable Lipschitz Certification for Generative Models

2021-07-06 · Matt Jordan, Alexandros G. Dimakis

We present a scalable technique for upper bounding the Lipschitz constant of generative models. We relate this quantity to the maximal norm over the set of attainable vector-Jacobian products of a given generative model.…