InKAN: B-Spline KANs via Truncated Power Form

arXiv:2609.01956 · cs.LG, cs.NA, math.NA · Submitted 2026-09-02 · Read on arXiv

cs.LG, cs.NA, math.NA

Submitted: 2026-09-02

Updated: 2026-09-05

Code: https://github.com/Blealtan/efficient-kan

Terminology

• Accuracy — 2× in this paper · explained in 1 episode
• Gradient Flow — 2× in this paper · explained in 2 episodes
• Actor — 1× in this paper · explained in 3 episodes
• Interpretability — 1× in this paper · explained in 15 episodes
• Kolmogorov-Arnold Networks (KANs) — 1× in this paper · explained in 3 episodes

Sources

• TruKAN: Towards More Efficient Kolmogorov-Arnold Networks Using Truncated Power Functions
• MatrixKAN: Parallelized Kolmogorov-Arnold Network
• Kolmogorov-Arnold Networks are Radial Basis Function Networks
• KAN: Kolmogorov-Arnold Networks
• Multilevel Training for Kolmogorov Arnold Networks

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks