We will cover two topics in random matrix theory. 1. Concentration inequalities. 2. Stochastic flow method. We will start with a review of basic results in random matrices like local laws and Dyson's Brownian motions. We will discuss coupling methods in random matrices...
Course description: This is a rigorous graduate-level course on optimization. The course covers convex and combinatorial optimization for solving large-scale problems. In recent years optimization has had a profound impact on machine learning, data...
This is a class about the digital economy, specifically the interplay between economic thinking and computational thinking as it relates to electronic commerce, incentives engineering, and networked systems. Topics covered vary each year, but include a subset of:
This is a graduate-level seminar course on robust machine learning. In recent years, advances in machine learning have brought forth unprecedented progress in artificial intelligence and predictive data analytics. Despite the empirical success of recent machine...
This is a graduate level course on optimization which provides a foundation for applications such as statistical machine learning, signal processing, finance, and approximation algorithms. The course will cover fundamental concepts in optimization theory, modeling, and algorithmic techniques... Read more about AM221. Advanced Optimization
An introduction to probabilistic reasoning for random structures, including random graphs, graphical models and Markov Random Fields (MRF). Topics include: large deviations theory and concentration inequalities Theory of random graphs,the moment method. Combinatorial...