Want to train KANS at scale? Now UKAN!

While Kolmogorov–Arnold Networks (KANs) are powerful MLP alternatives, their reliance on bounded grids limits their scalability and domain range. We propose Unbounded Kolmogorov–Arnold Networks (UKANs), which utilize a coefficient-generator (CG) model to dynamically produce B-spline coefficients on an unbounded symmetric grid. By integrating positional encodings, UKANs enable function approximation without data normalization. To address computational overhead, we introduce warpKAN, a GPU-accelerated library that optimizes memory management and reduces B-spline complexity proportional to grid size. Benchmarks show a $3\text{--}30\times$ speed-up and up to $1000\times$ memory reduction over vanilla KANs. Experiments across regression, classification, and generative tasks—including molecular property prediction—confirm that UKANs match or exceed KAN accuracy while enabling large-scale, end-to-end training.