This shows you the differences between two versions of the page.
Both sides previous revision Previous revision Next revision | Previous revision | ||
papers:collobert-weston-bottou-2006 [2006/08/02 18:30] leonb |
papers:collobert-weston-bottou-2006 [2007/01/31 14:45] leonb |
||
---|---|---|---|
Line 1: | Line 1: | ||
- | ===== Trading Convexity for Scalability ===== | ||
- | |||
- | <box 33% blue> | ||
- | < | ||
- | </ | ||
- | |||
- | // | ||
- | 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. | ||
- | we show how non-convexity can provide scalability advantages over | ||
- | convexity. | ||
- | (i) faster SVMs where training errors are no longer support vectors, and | ||
- | (ii) much faster Transductive SVMs. | ||
- | |||
- | |||
- | <box 99% orange> | ||
- | Ronan Collobert, Jason Weston and Léon Bottou: **Trading Convexity for Scalability**, | ||
- | |||
- | [[http:// | ||
- | [[http:// | ||
- | [[http:// | ||
- | </ | ||
- | |||
- | @inproceedings{collobert-weston-bottou-2006, | ||
- | author = {Collobert, Ronan and Weston, Jason and Bottou, L\' | ||
- | title = {Trading Convexity for Scalability}, | ||
- | year = {2006}, | ||
- | booktitle = {Proceedings of the Twenty-third International Conference on Machine Learning (ICML 2006)}, | ||
- | publisher = {IMLS/ | ||
- | note = {ACM Digital Library}, | ||
- | url = {http:// | ||
- | } | ||
- | |||
- | |||
- | ==== Links ==== | ||
- | |||
- | * The [[http:// | ||
- | * Home page of [[http:// | ||
- | * Home page of [[http:// | ||
- | * Home page of [[http:// | ||