Theoretical Foundations of Machine Learning Course 2025 Tweet

The course covers key algorithmic principles in machine learning and their theoretical foundations. Topics include statistical learning theory, linear and nonlinear models (kernel methods and neural networks), empirical risk minimization, regularization, functional analysis with focus on reproducing kernel Hilbert spaces, convex analysis, optimization methods (gradient, stochastic gradient, splitting methods, back-propagation), and statistical analysis using concentration of measure, empirical process theory, spectral calculus and operator theory. The program includes two tutorials by invited speakers.