Mathematical Optimization offers a unified framework for obtaining numerical solutions to data analytics problems, oftentimes with provable statistical guarantees of correctness at well-understood computational costs.


To this end, this course reviews recent advances in convex/non-convex optimization and statistical analysis in the context of contemporary Machine Learning Applications.


We provide an overview of the emerging data models and their statistical guarantees, describe scalable numerical solution techniques such as stochastic, first-order and primal-dual methods.