Learning rates of gradient descent algorithm for classification

Authors:
Xue-Mei Dong;Di-Rong Chen
Affiliations:
Department of Mathematics, Beijing University of Aeronautics and Astronautics, and LMIB of the Ministry of Education, Beijing 100083, China;Department of Mathematics, Beijing University of Aeronautics and Astronautics, and LMIB of the Ministry of Education, Beijing 100083, China
Venue:
Journal of Computational and Applied Mathematics
Year:
2009

Citing 9
Cited 0

Relative Loss Bounds for On-Line Density Estimation with the Exponential Family of Distributions

Machine Learning
Support vector machines are universally consistent

Journal of Complexity
Stability and generalization

The Journal of Machine Learning Research
Rademacher and gaussian complexities: risk bounds and structural results

The Journal of Machine Learning Research
Support Vector Machine Soft Margin Classifiers: Error Analysis

The Journal of Machine Learning Research
Online Learning Algorithms

Foundations of Computational Mathematics
Online learning with kernels

IEEE Transactions on Signal Processing
Online Regularized Classification Algorithms

IEEE Transactions on Information Theory
Worst-case quadratic loss bounds for prediction using linear functions and gradient descent

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	7.29

Visualization

Abstract

In this paper, a stochastic gradient descent algorithm is proposed for the binary classification problems based on general convex loss functions. It has computational superiority over the existing algorithms when the sample size is large. Under some reasonable assumptions on the hypothesis space and the underlying distribution, the learning rate of the algorithm has been established, which is faster than that of closely related algorithms.