This course provides a broad introduction to machine learning and statistical pattern recognition. Topics include: supervised learning (generative/discriminative learning, parametric/non-parametric learning, neural networks, support vector machines); unsupervised learning (clustering, dimensionality reduction, kernel methods); learning theory (bias/variance tradeoffs, practical advice); reinforcement learning and adaptive control. The course will also discuss recent applications of machine learning, such as to robotic control, data mining, autonomous navigation, bioinformatics, speech recognition, and text and web data processing.
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.
Prerequisites: Solid background of probability theory and mathematical statistics, convex optimization , and linear algebra.