Description
We discuss problems in unsupervised learning and introduce a statistical learning framework for learning data representation/reconstruction under constraints. We discuss the role played by regularization theory and regularized algorithms in this context.Slides
Slides for this lecture: PDF.Suggested Reading
1). A. Maurer and M. Pontil. K-dimensional coding schemes in Hilbert spaces. IEEE Transactions on Information Theory, 56(11): 5839-5846, 2010
2). David Arthur and Sergei Vassilvitskii. k-means++: the advantages of careful seeding. Proceedings of the eighteenth annual ACM-SIAM symposium on Discrete algorithms (SODA), 2007.
3). S. P. Lloyd, Least Squares Quantization in PCM, IEEE Trans. Information Theory, vol. 28, 129-137, 1982.