Learning capability of the rescaled pure greedy algorithm with non-iid sampling

Learning capability of the rescaled pure greedy algorithm with non-iid sampling

We consider the rescaled pure greedy learning algorithm (RPGLA) with the dependent samples drawn according to a non-identical sequence of probability distributions. The generalization performance is provided by applying the independent-blocks technique and adding the drift error. We derive the satis...

Full description

Bibliographic Details
Main Authors: Qin Guo, Binlei Cai
Format: Article
Language:English
Published: AIMS Press 2023-01-01
Series:Electronic Research Archive
Subjects:
rescaled pure greedy algorithm
$ \beta $-mixing
non-identical sequences
drift error
covering number
learning rate
Online Access:https://www.aimspress.com/article/doi/10.3934/era.2023071?viewType=HTML

Internet

https://www.aimspress.com/article/doi/10.3934/era.2023071?viewType=HTML

Similar Items