Intersections between Control, Learning and Optimization

February 24 - 28, 2020

Schedule


Monday, February 24, 2020

9:00 - 9:50
10:15 - 11:05
Dimitri Bertsekas (Massachusetts Institute of Technology and Arizona State University)

Distributed and Multiagent Reinforcement Learning
PDF Presentation

 
11:30 - 12:20
Csaba Szepesvari (University of Alberta)

Model misspecification in reinforcement learning
PDF Presentation

 
2:30 - 3:20
4:00 - 4:50

Tuesday, February 25, 2020

9:00 - 9:50
Russell Tedrake (Massachusetts Institute of Technology)

From pixels to torques: output feedback for robotics

 
10:15 - 11:05
Martin Riedmiller (DeepMind Technologies)

Learning Control from Minimal Prior Knowledge
PDF Presentation

 
11:30 - 12:20
Ben Recht (University of California, Berkeley (UC Berkeley))

Trying to Make Sense of Control from Pixels
PDF Presentation

 
2:30 - 3:20
4:00 - 4:50

Wednesday, February 26, 2020

9:00 - 9:50
10:15 - 11:05
Daniel Kuhn (École Polytechnique Fédérale de Lausanne (EPFL))

Wasserstein Distributionally Robust Optimization: Theory and Applications in Machine Learning
PDF Presentation

 
11:30 - 12:20
2:30 - 3:20
4:00 - 4:50
Francesco Borrelli (University of California, Berkeley (UC Berkeley))

Sample-Based Learning Model Predictive Control

 

Thursday, February 27, 2020

9:00 - 9:50
Maryam Fazel (University of Washington)

Finite-sample System Identification: Optimal Rates and the Role of Regularization

10:15 - 11:05
Richard Murray (California Institute of Technology)

Can We Really Use Machine Learning in Safety Critical Systems?
PDF Presentation

 
11:30 - 12:20
Dorsa Sadigh (Stanford University)

Beyond Theory of Mind: Learning and Influencing Conventions in Multi-Agent Interactions

 
2:30 - 3:20
James Rawlings (University of California, Santa Barbara (UCSB))

Industrial, large-scale model predictive control with deep neural networks
PDF Presentation

4:00 - 4:50
Stephen Wright (University of Wisconsin-Madison)

Nonconvex optimization in matrix optimization and distributionally robust optimization
PDF Presentation

 

Friday, February 28, 2020

9:00 - 9:10
Rohit Kannan (University of Wisconsin-Madison)

Predict, then smart optimize with stochastic programming

9:15 - 9:25
Sungho Shin (University of Wisconsin-Madison)

A Unifying Framework for Subspace Identification and Dynamic Mode Decomposition

9:30 - 9:40
Victor Magron (Laboratoire d'analyse et d'architecture des systèmes (LAAS-CNRS))

Polynomial Optimization for Bounding Lipschitz Constants of Deep Networks

9:45 - 9:55
Jia-Jie Zhu (Max Planck Institute for Intelligent Systems)

Distributionally Robust Optimization and Control using RKHS Embedding

10:15 - 11:05
Lieven Vandenberghe (University of California, Los Angeles (UCLA))

Bregman proximal methods for semidefinite optimization.
PDF Presentation

 
11:30 - 12:20