论文信息 - Stability of Unstable Learning Algorithms

Stability of Unstable Learning Algorithms

Abstract We introduce graphical learning algorithms and use them to produce bounds on error deviance for unstable learning algorithms which possess a partial form of stability. As an application we obtain error deviance bounds for support vector machines (SVMs) with variable offset parameter.

Don R. Hush | Ingo Steinwart | Clint Scovel

[1] Tong Zhang,et al. Convergence of Large Margin Separable Linear Classification , 2000, NIPS.

[2] Ingo Steinwart,et al. Sparseness of Support Vector Machines , 2003, J. Mach. Learn. Res..

[3] Vladimir N. Vapnik,et al. The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[4] Vladimir Vapnik,et al. Statistical learning theory , 1998 .

[5] Bernhard E. Boser,et al. A training algorithm for optimal margin classifiers , 1992, COLT '92.

[6] Partha Niyogi,et al. Almost-everywhere Algorithmic Stability and Generalization Error , 2002, UAI.

[7] André Elisseeff,et al. Stability and Generalization , 2002, J. Mach. Learn. Res..

[8] V. Barbu,et al. Convexity and optimization in banach spaces , 1972 .

[9] Ingo Steinwart,et al. Fast rates for support vector machines using Gaussian kernels , 2007, 0708.1838.