This paper tests whether Kolmogorov–Arnold Networks (KAN 2.0) are genuinely more noise-robust than Multi-Layer Perceptrons (MLP) and XGBoost for stellar classification (star/galaxy/quasar, 100,000 SDSS DR17 objects). A naive comparison suggests so: KAN retains +9 percentage points over MLP at SNR=5. But equalizing baseline accuracy via weight decay eliminates the gap — a properly regularized MLP matches KAN to within 1 p.p. at all SNR levels, both with and without spectroscopic redshift. The same holds on an independent DESI DR1 sample with different photometric bands. KAN's robustness thus traces to implicit regularization by C²-smooth B-spline activations, not to architecture. Per-class analysis (20 trials) shows that stars degrade fastest (F1: 0.97→0.75 at SNR=5), while QSOs remain stable. KAN's native feature importance and SHAP on MLP produce different rankings (Spearman ρ=−0.37), capturing complementary aspects of the classification. Colour-index features (u−g, g−r, r−i, i−z) widen KAN's relative advantage, and a hybrid pipeline routing uncertain MLP predictions to KAN improves low-SNR accuracy. KAN is best understood as a convenient auto-regularizer whose genuine advantage is built-in interpretability.
Kristian Sestak (Wed,) studied this question.