论文信息 - Generalization Guarantees for a Binary Classification Framework for Two-Stage Multiple Kernel Learning - 字舞流文

Generalization Guarantees for a Binary Classification Framework for Two-Stage Multiple Kernel Learning

We present generalization bounds for the TS-MKL framework for two stage multiple kernel learning. We also present bounds for sparse kernel learning formulations within the TS-MKL framework.

Purushottam Kar

[1] Koray Kavukcuoglu,et al. A Binary Classification Framework for Two-Stage Multiple Kernel Learning , 2012, ICML.

[2] M. Talagrand,et al. Probability in Banach Spaces: Isoperimetry and Processes , 1991 .

[3] Qiong Cao,et al. Generalization bounds for metric and similarity learning , 2012, Machine Learning.

[4] Maria-Florina Balcan,et al. On a theory of learning with similarity functions , 2006, ICML.

[5] Nathan Srebro,et al. How Good Is a Kernel When Used as a Similarity Measure? , 2007, COLT.

[6] Peter L. Bartlett,et al. Rademacher and Gaussian Complexities: Risk Bounds and Structural Results , 2003, J. Mach. Learn. Res..

[7] G. Lugosi,et al. Ranking and empirical minimization of U-statistics , 2006, math/0603123.

[8] Ambuj Tewari,et al. On the Complexity of Linear Prediction: Risk Bounds, Margin Bounds, and Regularization , 2008, NIPS.

[9] Ing Rj Ser. Approximation Theorems of Mathematical Statistics , 1980 .