Convergence analysis of online learning algorithm with two-stage step size
2021 ◽
Vol 0
(0)
◽
Keyword(s):
Abstract Online learning is a classical algorithm for optimization problems. Due to its low computational cost, it has been widely used in many aspects of machine learning and statistical learning. Its convergence performance depends heavily on the step size. In this paper, a two-stage step size is proposed for the unregularized online learning algorithm, based on reproducing Kernels. Theoretically, we prove that, such an algorithm can achieve a nearly min–max convergence rate, up to some logarithmic term, without any capacity condition.
Keyword(s):
Keyword(s):
2017 ◽
Vol 10
(13)
◽
pp. 284
2018 ◽
Vol 65
(11)
◽
pp. 1788-1792
◽
2019 ◽
Vol 33
◽
pp. 3232-3239
◽
2019 ◽
Vol 356
(13)
◽
pp. 7548-7570
◽