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

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.

arXiv comment27 pages, 9 figures

References in corpus (10)

• The automated computation of tree-level and next-to-leading order differential cross sections, and their matching to parton shower simulations
• The anti-k_t jet clustering algorithm
• DELPHES 3, A modular framework for fast simulation of a generic collider experiment
• A detailed map of Higgs boson interactions by the ATLAS experiment ten years after the discovery
• Observation of Higgs boson production in association with a top quark pair at the LHC with the ATLAS detector
• Observation of Single Top-Quark Production
• Observation of $\mathrm{t}\overline{\mathrm{t}}$H production
• Lifting degeneracies in Higgs couplings using single top production in association with a Higgs boson
• Modern Machine Learning and Particle Physics
• Indirect $\mathcal{C}\mathcal{P}$ probes of the Higgs-top-quark interaction: current LHC constraints and future opportunities

Cited by in corpus (1)

• Accurate Surrogate Amplitudes with Calibrated Uncertainties