EE 290: Mathematics of Data Science

Announcements

We will use Bcourses and this website for lecture notes and adminisitrative matters.

This course covers selected topics in the mathematical, statistical, and computational aspects of data science. We characterize the information-theoretic (statistical) limit for inference problems, investigate whether the statistical limits can be attained computationally efficiently, and analyze algorithmic techniques such as spectral methods, semidefinite programming relaxations, kernel methods, wavelet shrinkage. Specific topics will include spectral clustering, planted clique and partition problem, adaptive estimation, sparse PCA, community detection on stochastic block models, nonparametric function estimation and Lepski's method.

Solid background of probability theory and mathematical statistics (at the level of Stat 135 or EECS 126), convex optimization (at the level of EE 127 or CS 189), and linear algebra. Knowledge about information theory would help but is not a prerequisite.