Stability Analysis for Local Transductive Regression Algorithms

Wei Gao; Yun Gang Zhang; Li Liang

doi:10.4028/www.scientific.net/AMR.267.438

Paper Titles

An Algorithm to Eliminate Stochastic Jump Measurements of Ultrasonic Flow-Meter with Time Difference Method
p.414

Numerical Method of Hybrid Stochastic Functional Differential Equations with the Local Lipschitz Coefficients
p.422

A Discrete Data Fitting Models Fusing Genetic Algorithm
p.427

A Novel Method to Calculate Frequency Control Word of Direct Digital Synthesizer
p.433

Stability Analysis for Local Transductive Regression Algorithms
p.438

Data Stream Clustering Algorithm Based on Affinity Propagation and Density
p.444

New Criteria on Impulsive Stabilization and Synchronization of Delayed Unified Chaotic Systems with Uncertainty
p.450

Generalization Bounds for Certain Class of Ranking Algorithm
p.456

A New Method to Detect P-Wave Based on Quadratic Function
p.462

HomeAdvanced Materials ResearchAdvanced Materials Research Vol. 267Stability Analysis for Local Transductive...

Stability Analysis for Local Transductive Regression Algorithms

Abstract:

In this paper, the stability of local transductive regression algorithms is studied by adopting a strategy which adjusts the sample set by removing one or two elements from it. A sufficient condition for uniform stability is given. The result of our work shows that if a local transductive regression algorithm uses square loss, and if for any x, a kernel function K(x, x) has a limited upper bound, then the local transductive regression algorithm which minimizes the standard form will have good uniform stability.

You might also be interested in these eBooks

Manufacturing Systems and Industry Application

View Preview

Info:

Periodical:

Advanced Materials Research (Volume 267)

Pages:

438-443

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.267.438

Citation:

Cite this paper

Online since:

June 2011

Authors:

Wei Gao, Yun Gang Zhang, Li Liang

Keywords:

Algorithmic Stability, Cost Stability, Local Transductive Regression Algorithm, Pseudo-Target, Reproducing Kernel Hilbert Space, Transductive Learning

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] V.N. Vapnik: Estimation of Dependences Based on Empirical Data(Springer Publications, Berlin 1982).

Google Scholar

[2] O. Chapelle, V. Vapnik, and J. Weston, Transductive inference for estimating values of functions. In Neural Information Processing Systems, pp.421-427. MIT Press, (1999).

Google Scholar

[3] C. Cortes and M. Mohri, On transductive regression, In Advances in Neural Information Processing Systems, pp.305-312. MIT Press, (2007).

Google Scholar

[4] P. Derbeko, R. EI-Yaniv, and R. Meir, Explicit learning curves for transduction and application to clustering and compression algorithms, J. Artif. Intell. Res. (JAIR), Vol 22: 117-142, (2004).

DOI: 10.1613/jair.1417

Google Scholar

[5] R. EI-Yaniv, and D. Pechyony, Stable transductive learning, In Conference on Learning Theory, pp.35-49, Springer, (2006).

DOI: 10.1007/11776420_6

Google Scholar

[6] R. EI-Yaniv, and D. Pechyony, Transductive redemacher complexity and its applicatons, In Conference on Learning Theory, pp.35-49, Springer, (2007).

Google Scholar

[7] M. Wu and B. Schlkopf, Transductive classification via local learning regularization, In Artificial Intelligence and Statistics, (2007).

Google Scholar

[8] C. Cortes, M. Mohri, D. Pechyony, and A. Rastogi, Stability Analysis and Learning Bounds for Transductive Regression Algorithms, Submitted.

DOI: 10.1145/1390156.1390179

Google Scholar