Abstract
In this session, we will provide an overview of stochastic and robust optimization, with problems in statistics and machine learning providing a motivating focus. We will discuss connections between convex optimization and regret minimization, both with stochastic and deterministic feedback. We will view these problems through the minimax lens and show how algorithms emerge as approximate dynamic programming solutions. Finally, we will review robust optimization and explore the interactions between robustness and regularization.
The first session of this mini course will take place on Tuesday, August 22 from 3:00 - 4:00 PM; the second session of this mini course will take place on Tuesday, August 22 from 4:30 - 5:30 PM; the third session of this mini course will take place on Wednesday, August 23 from 4:30 - 5:30 PM.