KAN we improve on HEP classification tasks? Kolmogorov-Arnold Networks applied to an LHC physics example

TL;DR

This paper evaluates Kolmogorov-Arnold Networks (KANs) for high-energy physics classification tasks, comparing their performance and interpretability to traditional neural networks, and finds small KANs offer interpretability with moderate performance trade-offs.

Contribution

The study applies KANs to a high-energy physics classification problem, analyzing their performance, interpretability, and how they compare to multilayer perceptrons in this context.

Findings

KANs learn activation functions resembling log-likelihood ratios

Deeper KANs learn more complex data representations

Small KANs offer interpretability with moderate performance loss

Abstract

Recently, Kolmogorov-Arnold Networks (KANs) have been proposed as an alternative to multilayer perceptrons, suggesting advantages in performance and interpretability. We study a typical binary event classification task in high-energy physics including high-level features and comment on the performance and interpretability of KANs in this context. Consistent with expectations, we find that the learned activation functions of a one-layer KAN resemble the univariate log-likelihood ratios of the respective input features. In deeper KANs, the activations in the first layer differ from those in the one-layer KAN, which indicates that the deeper KANs learn more complex representations of the data, a pattern commonly observed in other deep-learning architectures. We study KANs with different depths and widths and we compare them to multilayer perceptrons in terms of performance and number of trainable parameters. For the chosen classification task, we do not find that KANs are more parameter efficient. However, small KANs may offer advantages in terms of interpretability that come at the cost of only a moderate loss in performance.