Abstract: Convex learning algorithms, such as Support Vector Machines (SVMs), are often seen as highly desirable because they offer strong practical properties and are amenable to theoretical analysis. However, in this work we show how non-convexity can provide scalability advantages over convexity. We show how concave-convex programming can be applied to produce (i) faster SVMs where training errors are no longer support vectors, and (ii) much faster Transductive SVMs.
@inproceedings{collobert-weston-bottou-2006,
author = {Collobert, Ronan and Weston, Jason and Bottou, L\'{e}on},
title = {Trading Convexity for Scalability},
year = {2006},
booktitle = {Proceedings of the Twenty-third International Conference on Machine Learning (ICML 2006)},
publisher = {IMLS/ICML},
note = {ACM Digital Library},
url = {http://leon.bottou.org/papers/collobert-weston-bottou-2006},
}