Convergence of Unregularized Online Learning Algorithms

Preprint English OPEN
Lei, Yunwen; Shi, Lei; Guo, Zheng-Chu;
  • Subject: Computer Science - Learning

In this paper we study the convergence of online gradient descent algorithms in reproducing kernel Hilbert spaces (RKHSs) without regularization. We establish a sufficient condition and a necessary condition for the convergence of excess generalization errors in expecta... View more
Share - Bookmark