Fall 2021 – SILO

Exploring the limits of large scale pre-training

Hanie Sedghi
Google Research, Brain Team

Model Projections in Model Space (MPMS): A geometric interpretation of the AIC and estimating the distance between the generating process and the best approximating model

Jose Miguel Ponciano
University of Florida

Game Redesign in No-regret Game Playing

Jerry Zhu
University of Wisconsin–Madison

Over-parametrized Matrix Estimation

Yudong Chen
University of Wisconsin–Madison

Averaging Connectomes: Beyond the Arithmetic Mean

Keith Levin
University of Wisconsin–Madison

Reinforcement Learning for Markov Games

Qiaomin Xie
University of Wisconsin–Madison

Brown Bag Lunch

Talk postponed to 12/15/2021 Brown Bag lunch discussion instead.

Towards Data Efficient Monte Carlo Estimates in Reinforcement Learning

Josiah Hanna
University of Wisconsin–Madison

Dictionary Learning from dependent data samples

Hanback Lyu
University of Wisconsin–Madison

Learning from preferences and labels

Aarti Singh
Carnegie Mellon University