Abstract
We present a method which uses example pairs of equal or unequal class labels to select a subspace with near optimal metric properties in a kernel-induced Hilbert space. A representation of finite dimensional projections as bounded linear functionals on a space of Hilbert-Schmidt operators leads to PAC-type performance guarantees for the resulting feature maps. The proposed algorithm returns the projection onto the span of the principal eigenvectors of an empirical operator constructed in terms of the example pairs. It can be applied to meta-learning environments and experiments demonstrate an effective transfer of knowledge between different but related learning tasks.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Bartlett, P.L., Mendelson, S.: Rademacher and Gaussian Complexities: Risk Bounds and Structural Results. Journal of Machine Learning Research (2002)
Bartlett, P., Bousquet, O., Mendelson, S.: Local Rademacher complexities, Available online: http://www.stat.berkeley.edu/~bartlett/papers/bbm-lrc-02b.pdf
Bar-Hillel, A., Hertz, T., Shental, N., Weinshall, D.: Learning a Mahalanobis Metric from Equivalence Constraints. Journal of Machine Learning Research 6, 937–965 (2005)
Baxter, J.: A Model of Inductive Bias Learning. Journal of Artificial Intelligence Research 12, 149–198 (2000)
Cristianini, N., Shawe-Taylor, J.: Support Vector Machines. Cambridge University Press, Cambridge (2000)
Hammer, R., Hertz, T., Hochstein, S., Weinshall, D.: Category learning from equivalence constraints. In: XXVII Conference of Cognitive Science Society (CogSci 2005) (available online)
Koltchinskii, V., Panchenko, D.: Empirical margin distributions and bounding the generalization error of combined classifiers. The Annals of Statistics 30(1), 1–50
Ledoux, M., Talagrand, M.: Probability in Banach Spaces: isoperimetry and processes. Springer, Heidelberg (1991)
McDiarmid, C.: Concentration. In: Probabilistic Methods of Algorithmic Discrete Mathematics, pp. 195–248. Springer, Berlin (1998)
Mika, S., Schölkopf, B., Smola, A., Müller, K.-R., Scholz, M., Rätsch, G.: Kernel PCA and De-noising in Feature Spaces. Advances in Neural Information Processing Systems 11 (1998)
Shawe-Taylor, J., Christianini, N.: Estimating the moments of a random vector. In: Proceedings of GRETSI 2003 Conference, vol. I, pp. 47–52 (2003)
Reed, M., Simon, B.: Functional Analysis, part I of Methods of Mathematical Physics. Academic Press, London (1980)
Robins, A.: Transfer in Cognition. In: Thrun, S., Pratt, L. (eds.) Learning to Learn. Springer, Heidelberg (1998)
Shawe-Taylor, J., Williams, C.K.I., Cristianini, N., Kandola, J.S.: On the eigenspectrum of the gram matrix and the generalization error of kernel-PCA. IEEE Transactions on Information Theory 51(7), 2510–2522 (2005)
Thrun, S.: Lifelong Learning Algorithms. In: Thrun, S., Pratt, L. (eds.) Learning to Learn. Springer, Heidelberg (1998)
Xing, E.P., Ng, A.Y., Jordan, M.I., Russel, S.: Distance metric learning, with application to clustering with side information. In: Becker, S., Thrun, S., Obermayer, K. (eds.) Advances in Neural Information Processing Systems, vol. 14, MIT Press, Cambridge (2002)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Maurer, A. (2006). Generalization Bounds for Subspace Selection and Hyperbolic PCA. In: Saunders, C., Grobelnik, M., Gunn, S., Shawe-Taylor, J. (eds) Subspace, Latent Structure and Feature Selection. SLSFS 2005. Lecture Notes in Computer Science, vol 3940. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11752790_13
Download citation
DOI: https://doi.org/10.1007/11752790_13
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-34137-6
Online ISBN: 978-3-540-34138-3
eBook Packages: Computer ScienceComputer Science (R0)