3 papers
cs.LG2026
Optimized Architectures for Kolmogorov-Arnold Networks
James Bagrow, Josh Bongard
Efforts to improve Kolmogorov--Arnold networks (KANs) with architectural enhancements have been stymied by the complexity those enhancements bring, undermining the interpretability…
cs.LG2025
Softly Symbolifying Kolmogorov-Arnold Networks
James Bagrow, Josh Bongard
Kolmogorov-Arnold Networks (KANs) offer a promising path toward interpretable machine learning: their learnable activations can be studied individually, while collectively fitting…
cs.LG2025
Multi-Exit Kolmogorov-Arnold Networks: enhancing accuracy and parsimony
James Bagrow, Josh Bongard
Kolmogorov-Arnold Networks (KANs) uniquely combine high accuracy with interpretability, making them valuable for scientific modeling. However, it is unclear a priori how deep a net…