Stochastic optimization (SO) methods are optimization techniques that use random variables in the formulation of the problem or in the iterates. These methods generalize deterministic methods for deterministic problems and can be used to solve stochastic problems. They combine both meanings of stochastic optimization, using random objective functions or constraints and random iterates.

This course investigates the mathematical principles behind data and information analysis. It brings together concepts from statistics, optimization, and computer science, with a focus on large deviation inequalities, and convex analysis. It's tailored towards advanced graduate students who wish to incorporate these theories into their research.