nips nips2004 nips2004-168 nips2004-168-reference knowledge-graph by maker-knowledge-mining

168 nips-2004-Semigroup Kernels on Finite Sets


Source: pdf

Author: Marco Cuturi, Jean-philippe Vert

Abstract: Complex objects can often be conveniently represented by finite sets of simpler components, such as images by sets of patches or texts by bags of words. We study the class of positive definite (p.d.) kernels for two such objects that can be expressed as a function of the merger of their respective sets of components. We prove a general integral representation of such kernels and present two particular examples. One of them leads to a kernel for sets of points living in a space endowed itself with a positive definite kernel. We provide experimental results on a benchmark experiment of handwritten digits image classification which illustrate the validity of the approach. 1


reference text

[1] B. Sch¨ lkopf and A.J. Smola. Learning with Kernels: Support Vector Machines, Regularization, o Optimization, and Beyond. MIT Press, Cambridge, MA, 2002.

[2] J. Lafferty and G. Lebanon. Information diffusion kernels. In Advances in Neural Information Processing Systems 14, Cambridge, MA, 2002. MIT Press.

[3] M. Seeger. Covariance kernels from bayesian generative models. In Advances in Neural Information Processing Systems 14, pages 905–912, Cambridge, MA, 2002. MIT Press.

[4] R. Kondor and T. Jebara. A kernel between sets of vectors. In Machine Learning, Proceedings of the Twentieth International Conference (ICML 2003), pages 361–368. AAAI Press, 2003.

[5] L. Wolf and A. Shashua. Learning over sets using kernel principal angles. Journal of Machine Learning Research, 4:913–931, 2003.

[6] F. Bach and M. Jordan. Kernel independent component analysis. Journal of Machine Learning Research, 3:1–48, 2002.

[7] M. Cuturi and J.-P. Vert. A mutual information kernel for sequences. In IEEE International Joint Conference on Neural Networks, 2004.

[8] C. Berg, J.P.R. Christensen, and P. Ressel. Harmonic Analysis on Semigroups. Springer, 1984.

[9] S. Amari and H. Nagaoka. Methods of information geometry. AMS vol. 191, 2001.

[10] F. M. J. Willems, Y. M. Shtarkov, and Tj. J. Tjalkens. The context-tree weighting method: basic properties. IEEE Transancations on Information Theory, pages 653–664, 1995.

[11] J.-P. Vert, H. Saigo, and T. Akutsu. Local alignment kernels for protein sequences. In B. Schoelkopf, K. Tsuda, and J.-P. Vert, editors, Kernel Methods in Computational Biology. MIT Press, 2004.

[12] T. Cover and J. Thomas. Elements of Information Theory. Wiley & Sons, New-York, 1991.

[13] N. Aronszajn. Theory of reproducing kernels. Transactions of the American Mathematical Society, 68:337 – 404, 1950.