ELLIS Delft Talk by Peyman Mohajerin Esfahani: The Role of Convexity in Learning: An Inverse Optimization Case Study
07 mei 2024 16:00 t/m 17:00 - Locatie: Building 28, Van Mourik Broekmanweg 6, Room Hilbert - Door: ELLIS Delft | Zet in mijn agenda
by Payman Mohajerin Esfahani | Delft University of Technology
Abstract
In this talk, I briefly review a general class of data-driven decision-making and highlight the role of convexity in addressing three research questions that arise in this context. Next, I focus on a particular setting of such problems known as inverse optimization where the goal is to replicate the behavior of a decision-maker with an unknown objective function. We discuss recent developments in this setting concerning convex training losses and optimization algorithms. We motivate the discussion with applications from control (learning the MPC control law), transportation (the 2021 Amazon Routing Problem Challenge), and robotics (comparison with the state-of-the-art in the MuJoCo environments).
This meeting is open for all interested researchers, and we particularly want to emphasize that we very much welcome all the PhD students and postdocs that are associated with the unit! If you have ideas about ways to make these talks more engaging for you, please let us know your suggestions.