AI RESEARCH
Wahkon: A Statistically Principled Deep RKHS Superposition Network
arXiv CS.LG
•
ArXi:2605.14041v1 Announce Type: cross Deep learning excels at prediction but often lacks finite-sample guarantees and calibrated uncertainty; RKHS (Reproducing Kernel Hilbert Space)-based methods provide those guarantees but struggle to adapt in high dimensions. We propose Wahkon, a deep RKHS superposition network that unifies Kolmogoro's superposition principle with RKHS regularization in the smoothing-spline tradition of Wahba. This yields a finite-dimensional deep representer theorem that makes.