Infinite SVM: A Dirichlet Process Mixture of Large-Margin Kernel Machines
Abstract
We present Infinite SVM (iSVM), a Dirichlet process mixture of large-margin kernel machines for multi-way classification. An iSVM enjoys the advantages of both Bayesian nonparametrics in handling the unknown number of mixing components, and large-margin kernel machines in robustly capturing local nonlinearity of complex data. We develop an efficient variational learning algorithm for posterior inference of iSVM, and we demonstrate the advantages of iSVM over Dirichlet process mixture of generalized linear models and other benchmarks on both synthetic and real Flickr image classification datasets.
Cite
Text
Zhu et al. "Infinite SVM: A Dirichlet Process Mixture of Large-Margin Kernel Machines." International Conference on Machine Learning, 2011.Markdown
[Zhu et al. "Infinite SVM: A Dirichlet Process Mixture of Large-Margin Kernel Machines." International Conference on Machine Learning, 2011.](https://mlanthology.org/icml/2011/zhu2011icml-infinite/)BibTeX
@inproceedings{zhu2011icml-infinite,
title = {{Infinite SVM: A Dirichlet Process Mixture of Large-Margin Kernel Machines}},
author = {Zhu, Jun and Chen, Ning and Xing, Eric P.},
booktitle = {International Conference on Machine Learning},
year = {2011},
pages = {617-624},
url = {https://mlanthology.org/icml/2011/zhu2011icml-infinite/}
}