Machine Learning and Friends Lunch: Dylan Foster, Understanding the foundation model pipeline: From imitation to exploration
Content
Speaker
Dylan Foster (Microsoft Research; incoming assistant professor at UC Berkeley)
Abstract
The prevailing recipe of ever-larger models trained on passively collected data is showing diminishing returns and facing growing constraints on data. To sustain progress, the next phase of AI will hinge on experience: agents and systems that actively curate their own data through interaction. This talk asks: which principles behind today's foundation model pipeline will carry us there, and where do we need new ones?
Speaker Bio
Dylan Foster is an incoming assistant professor in EECS and Statistics at UC Berkeley, and a principal researcher at Microsoft Research, New England and New York City. Previously, he was a postdoctoral fellow at MIT IDSS with Sasha Rakhlin, and received his PhD from the Department of Computer Science at Cornell University, advised by Karthik Sridharan. His research develops principles and algorithms for learning from interaction, including reinforcement learning, foundation model training, and interactive decision making. His work has received several awards, including best paper at COLT (2019), best student paper at COLT (2018, 2019), and the Cornell CS doctoral dissertation award.