Trading convexity for scalability

Trading convexity for scalability (2006)

Cached

Download Links

Other Repositories/Bibliography

DBLP

by Ronan Collobert , Fabian Sinz , Jason Weston , Léon Bottou

Venue:	ICML06, 23rd International Conference on Machine Learning
Citations:	33 - 2 self

BibTeX

@INPROCEEDINGS{Collobert06tradingconvexity,
    author = {Ronan Collobert and Fabian Sinz and Jason Weston and Léon Bottou},
    title = {Trading convexity for scalability},
    booktitle = {ICML06, 23rd International Conference on Machine Learning},
    year = {2006},
    pages = {201--208},
    publisher = {ACM Press}
}

Years of Citing Articles

Bookmark

OpenURL

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. 1.

Citations

6696	The Nature of Statistical Learning Theory - Vapnik - 1995
1512	Smola A: Learning with Kernels - Schölkopf - 2002
1325	Experiments with a new boosting algorithm - Freund, Schapire - 1996
801	A probabilistic theory of pattern recognition - Devroye, Györfi, et al. - 1996
758	JC: Fast Training of Support Vector Machines using Sequential Minimal Optimization - Platt - 1998
509	Transductive inference for text classification using support vector machines - Joachims - 1999
312	RCV1: A New Benchmark Collection for Text Categorization Research - Lewis, Yang, et al. - 2004
146	Semi-supervised support vector machines - Bennet, Demiriz - 1998
93	Efficient BackProp - LeCun, Bottou, et al. - 1998
89	Semi-supervised classification by low density separation - Chapelle, Zien - 2005
81	Sparseness of support vector machines - Steinwart - 1071
72	A probability analysis on the value of unlabeled data for classification problems - Zhang, Oles - 2000
52	Improved generalization through explicit optimization of margins - Mason, Bartlett, et al. - 1999
49	Maximum margin clustering - Xu, Neufeld, et al. - 2005
47	Une approche theorique de l'apprentissage connexioniste� applications a la reconnaissance de la parole - Bottou - 1991
38	Introduction à l’analyse numérique matricielle et à l’optimisation - Ciarlet - 1982
36	Boosting neural networks - Schwenk, Bengio - 2000
36	Semi-supervised support vector machines for unlabeled data classification - Fung, Mangasarian - 1999
35	Kernel methods for missing variables - Smola, Vishwanathan, et al. - 2005
30	N.: Convex methods for transduction - Bie, Cristianini - 2004
24	The concaveconvex procedure (cccp - Yuille, Rangarajan - 2003
16	Multicategory ψ-learning and support vector machine: computational tools - Liu, Shen, et al. - 2005
11	On psi-learning - Shen, Tseng, et al. - 2003
11	Leveraging the Margin More Carefully - Krause, Singer - 2004
5	Empirical Risk Minimization for Support Vector Classifiers - Perez-Cruz, Navia-Vazquez, et al. - 2002
5	Fast rates to bayes for kernel machines - Steinwart, Scovel - 2005
3	Analyse numérique des algorithmes de l’optimisation d.c. approches locales et globale. codes et simulations numériques en grande dimension. applications. Doctoral dissertation - Thi - 1994
3	Multicategory psi-learning and support vector machine: computational tools - Liu, Shen, et al. - 2005
1	Trading Convexity for Scalability - Krause, Singer - 2004