Max-Margin Stacking and Sparse Regularization for Linear Classifier Combination and Selection

Details Max-Margin Stacking and Sparse Regularization for Linear Classifier Combination and Selection Max-Margin Stacking and Sparse Regularization for Linear Classifier Combination and Selection

2011-06-08

arxiv.org/abs/1106.1684v1

Computer Science

Learning

8 pages, 3 figures, 6 tables, journal

Scientific paper

The main principle of stacked generalization (or Stacking) is using a second-level generalizer to combine the outputs of base classifiers in an ensemble. In this paper, we investigate different combination types under the stacking framework; namely weighted sum (WS), class-dependent weighted sum (CWS) and linear stacked generalization (LSG). For learning the weights, we propose using regularized empirical risk minimization with the hinge loss. In addition, we propose using group sparsity for regularization to facilitate classifier selection. We performed experiments using two different ensemble setups with differing diversities on 8 real-world datasets. Results show the power of regularized learning with the hinge loss function. Using sparse regularization, we are able to reduce the number of selected classifiers of the diverse ensemble without sacrificing accuracy. With the non-diverse ensembles, we even gain accuracy on average by using sparse regularization.

Affiliated with

Also associated with

No associations

Rating

Max-Margin Stacking and Sparse Regularization for Linear Classifier Combination and Selection does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Max-Margin Stacking and Sparse Regularization for Linear Classifier Combination and Selection, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Max-Margin Stacking and Sparse Regularization for Linear Classifier Combination and Selection will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-578653