AI RESEARCH
Dynamic Regret for Online Regression in RKHS via Discounted VAW and Subspace Approximation
arXiv CS.LG
•
ArXi:2604.25021v1 Announce Type: new We study online regression with the square loss in a reproducing kernel Hilbert space under a dynamic regret criterion. The learner is compared with a time-varying comparator sequence, and the bounds depend on its path length in the RKHS norm. The proposed method transfers the finite-dimensional discounted Vovk--Azoury--Warmuth approach of Jacobsen \& Cutkosky to the RKHS setting by means of finite-dimensional subspace approximations.