Recent topics include: Graphical models and approximate inference algorithms. Markov chain Monte Carlo, mean field and probability propagation methods. Model selection and stochastic realization. Bayesian information theoretic and structural risk minimization approaches. Markov decision processes and partially observable Markov decision processes. Reinforcement learning.

We will take a guided tour of both basic and advanced methods in statistical machine learning, and the accompanying analysis tools that enable us to understand them theoretically. Theorems are presented together with practical aspects of methodology and intuition to help students develop a broad sense of the rationale (pros and cons) behind choosing to use a given method/approach in particular problem settings. Topics to be covered will most likely include: high-dimensional estimation, nonparametric regression and testing, overparametrization and interpolation, model selection, predictive inference, and distribution-free uncertainty quantification.

Repeat Rules

Course is not repeatable for credit.