Fast Fisher discriminant analysis with randomized algorithms

•We propose to use random projection to accelerate Fisher discriminant analysis and provide a theoretical analysis. Empirical study shows our method is effective and efficient.•We propose to use random feature map to accelerate kernel discriminant analysis. And we provide theoretical and empirical a...

Full description

Saved in:
Bibliographic Details
Published in:Pattern recognition Vol. 72; pp. 82 - 92
Main Authors: Ye, Haishan, Li, Yujun, Chen, Cheng, Zhang, Zhihua
Format: Journal Article
Language:English
Published: Elsevier Ltd 01.12.2017
Subjects:
Fisher discriminant analysis
Random feature map
Random projection
Random feature map
Random projection
Fisher discriminant analysis
ISSN:0031-3203, 1873-5142
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:•We propose to use random projection to accelerate Fisher discriminant analysis and provide a theoretical analysis. Empirical study shows our method is effective and efficient.•We propose to use random feature map to accelerate kernel discriminant analysis. And we provide theoretical and empirical analysis to show the effectiveness and efficiency of our methods. Fisher discriminant analysis is a classical method for classification and dimension reduction jointly. Regularized FDA (RFDA) and kernel FAD (KFDA) are two important variants. However, RFDA will get stuck in computational burden due to either the high dimension of data or the big number of data and KFDA has similar computational burden due to kernel operations. We propose fast FDA algorithms based on random projection and random feature map to accelerate FDA and kernel FDA. We give theoretical guarantee that the fast FDA algorithms using random projection have good generalization ability in comparison with the conventional regularized FDA. We also give a theoretical guarantee that the pseudoinverse FDA based on random feature map can share similar generalization ability with the conventional kernel FDA. Experimental results further validate that our methods are powerful.
ISSN:0031-3203
1873-5142
DOI:10.1016/j.patcog.2017.06.029