An envelope time-delay Kolmogorov-Arnold Network (ETDKAN) for DPD in A-RoF systems matches MLP performance on ACLR/EVM with complexity near memory polynomials and yields 4-5 dB ACLR improvement in experiment.
hub
Kan or mlp: A fairer comparison
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
abstract
This paper does not introduce a novel method. Instead, it offers a fairer and more comprehensive comparison of KAN and MLP models across various tasks, including machine learning, computer vision, audio processing, natural language processing, and symbolic formula representation. Specifically, we control the number of parameters and FLOPs to compare the performance of KAN and MLP. Our main observation is that, except for symbolic formula representation tasks, MLP generally outperforms KAN. We also conduct ablation studies on KAN and find that its advantage in symbolic formula representation mainly stems from its B-spline activation function. When B-spline is applied to MLP, performance in symbolic formula representation significantly improves, surpassing or matching that of KAN. However, in other tasks where MLP already excels over KAN, B-spline does not substantially enhance MLP's performance. Furthermore, we find that KAN's forgetting issue is more severe than that of MLP in a standard class-incremental continual learning setting, which differs from the findings reported in the KAN paper. We hope these results provide insights for future research on KAN and other MLP alternatives. Project link: https://github.com/yu-rp/KANbeFair
hub tools
citation-role summary
background 1
baseline 1
citation-polarity summary
representative citing papers
Adaptive RBF-KAN adds multiple radial basis kernels and LOOCV-based shape initialization to FastKAN, with benchmark tests on 2D functions showing kernel-specific advantages for smooth, discontinuous, and oscillatory cases.
ActNet is a new KST-based neural network that outperforms KANs and competes with MLPs in PINN benchmarks for PDE simulation tasks.
KLT-Net reconstructs the SN Ia distance modulus non-parametrically; with MFV M_B and flat-ΛCDM Bayesian/Hessian inference it yields H0 ≈ 69.6 km s⁻¹ Mpc⁻¹ and Ωm ≈ 0.30.
Platform-independent formulas for KAN hardware inference complexity (RM, BOP, NABS) are derived for B-spline, GRBF, Chebyshev, and Fourier variants.
Logistic KAN and KAAM achieve competitive or superior accuracy on clinical datasets compared to linear, tree, and neural baselines while providing built-in interpretability via symbolic forms and feature-wise decompositions.
P1-KAN introduces a new KAN architecture with theoretical approximation guarantees that outperforms MLPs and prior KAN variants on irregular functions while matching spline KAN accuracy on smooth ones, demonstrated on hydraulic optimization.
KANs achieve good but marginally inferior performance to MLPs for airfoil pressure coefficient prediction while being simpler and faster to train, though unstable and hyperparameter-sensitive; GNNs perform best.
A systematic review of Kolmogorov-Arnold Networks that maps their relation to Kolmogorov superposition theory, MLPs, and kernels, examines basis-function design choices, summarizes performance advances, and supplies a practitioner's selection guide plus open challenges.
A review arguing that Kolmogorov-Arnold Networks address key limitations of deep learning models for EEG-based seizure detection through improved interpretability and efficiency.
citing papers explorer
-
Low Complexity Kolmogorov-Arnold Network-based DPD for Analog RoF Fronthaul
An envelope time-delay Kolmogorov-Arnold Network (ETDKAN) for DPD in A-RoF systems matches MLP performance on ACLR/EVM with complexity near memory polynomials and yields 4-5 dB ACLR improvement in experiment.
-
Adaptive RBF-KAN: A Comparative Evaluation of Dynamic Shape Parameters in Kolmogorov-Arnold Networks
Adaptive RBF-KAN adds multiple radial basis kernels and LOOCV-based shape initialization to FastKAN, with benchmark tests on 2D functions showing kernel-specific advantages for smooth, discontinuous, and oscillatory cases.
-
Deep Learning Alternatives of the Kolmogorov Superposition Theorem
ActNet is a new KST-based neural network that outperforms KANs and competes with MLPs in PINN benchmarks for PDE simulation tasks.
-
KAN-LSTM-Transformer Neural Networks, MFV and Cosmological Parameters
KLT-Net reconstructs the SN Ia distance modulus non-parametrically; with MFV M_B and flat-ΛCDM Bayesian/Hessian inference it yields H0 ≈ 69.6 km s⁻¹ Mpc⁻¹ and Ωm ≈ 0.30.
-
Hardware-Oriented Inference Complexity of Kolmogorov-Arnold Networks
Platform-independent formulas for KAN hardware inference complexity (RM, BOP, NABS) are derived for B-spline, GRBF, Chebyshev, and Fourier variants.
-
Interpretable Clinical Classification with Kolmogorov-Arnold Networks
Logistic KAN and KAAM achieve competitive or superior accuracy on clinical datasets compared to linear, tree, and neural baselines while providing built-in interpretability via symbolic forms and feature-wise decompositions.
-
P1-KAN: an effective Kolmogorov-Arnold network with application to hydraulic valley optimization
P1-KAN introduces a new KAN architecture with theoretical approximation guarantees that outperforms MLPs and prior KAN variants on irregular functions while matching spline KAN accuracy on smooth ones, demonstrated on hydraulic optimization.
-
Kolmogorov Arnold networks (KAN) for aerodynamic prediction: a comparison with MLPs and GNNs
KANs achieve good but marginally inferior performance to MLPs for airfoil pressure coefficient prediction while being simpler and faster to train, though unstable and hyperparameter-sensitive; GNNs perform best.
-
A Practitioner's Guide to Kolmogorov-Arnold Networks
A systematic review of Kolmogorov-Arnold Networks that maps their relation to Kolmogorov superposition theory, MLPs, and kernels, examines basis-function design choices, summarizes performance advances, and supplies a practitioner's selection guide plus open challenges.
-
From Handcrafted Features to Functional Edge Learning: Evolution of EEG Seizure Detection Frameworks
A review arguing that Kolmogorov-Arnold Networks address key limitations of deep learning models for EEG-based seizure detection through improved interpretability and efficiency.