Lecture 1: Unifying the Analysis in Control and Optimization via Semidefinite Programs
Lecture 2: Uncertainty Modeling and Robustness Analysis
Lecture 3: Beyond Time-Invariant Models
Lecture 4: Empirical Risk Minimization: A General Paradigm for Machine Learning
Lecture 5: Connection between Stochastic Optimization Methods and Feedback Systems
Lecture 6: Dissipation Inequality for Stochastic Finite-Sum Methods
Lecture 7: Supply Rate Constructions and Quadratic Constraints, Part I
Lecture 8: Supply Rate Constructions and Quadratic Constraints, Part II
Lecture 9: Supply Rate Constructions for Stochastic Finite-Sum Methods
Lecture 10: Lure-Postnikov Lyapunov Functions
Lecture 11: Incorporating Dynamics into IQCs
Lecture 12: Zames-Falb IQCs for Convergence Rate Analysis