[Sds-seminars] FW: S&DS Seminar, Max Simchowitz, 1/29/24, 4pm-5pm, Kline Tower, "Mathematical Foundations for Physical Agents"

[elizavette.torres at yale.edu]

 <https://statistics.yale.edu/>     <https://statistics.yale.edu/>
Department of Statistics and Data Science  


 <https://statistics.yale.edu/seminars/max-simchowitz> Max Simchowitz,
Massachusetts Institute of Technology


Date: Monday, January 29, 2024

Time: 4:00PM to 5:00PM

Location: Kline Tower
<http://maps.google.com/?q=219+Prospect+Street%2C+13th+Floor%2C+Room+1327%2C
+New+Haven%2C+CT%2C+06511%2C+us> see map 

219 Prospect Street, 13th Floor, Room 1327

New Haven, CT 06511

Zoom Option:  Link: https://yale.zoom.us/j/94223816617 Meeting ID: 942 2381
6617

 <https://msimchowitz.github.io/> Website 

Mathematical Foundations for Physical Agents

 

Information and Abstract: From robotics to autonomous vehicles, machine
learning agents deployed in the physical world ("physical agents") promise
to revolutionize endeavors ranging from manufacturing to agriculture to
domestic labor. In this talk, we will develop mathematical foundations, from
the ground up, for how to carry out this vision. We will begin our
investigation by examining linear dynamical systems, a simple and
fundamental model of the interaction between a physical agent and its
environment. We prove mathematically that simple exploration attains optimal
performance for some of both the simplest and the most complex learning
problems in this class. The above finding, while powerful, strongly
motivates moving past linear dynamics as a mathematical testbed for
understanding learning with physical agents. 

Hence, we turn to providing mathematical guarantees for a setting of
real-world importance that does not fit the linear mold: behavior cloning.
Behavior cloning - teaching a robot to imitate from example demonstrations -
lies at the heart of many of today's most promising robot learning endeavors
due to its intuitive data collection and simplicity. Though it can work
incredibly well, we still do not have a clear understanding of what
circumstances ensure its success. Bringing together the flexibility of
generative models with key intuitions arising from the study of linear
control,  we introduce a framework for behavior cloning that enables an
agent to imitate nearly arbitrary behavior with provable guarantees, even
when the dynamics governing the agent and environments interaction are
nonlinear. We conclude by outlining ongoing work and future steps towards
building out the mathematical and conceptual tooling for understanding the
next steps towards general, capable and flexible physical agents. 

Bio: Max Simchowitz is a postdoctoral researcher in the Robot Locomotion
Group at MIT CSAIL. He studies the theoretical foundations of machine
learning problems with a sequential or dynamical component; he currently
focuses on robotics and out-of-distribution learning, and with past work
ranging broadly across control, reinforcement learning, optimization and
algorithmic fairness. He received his PhD from University of California,
Berkeley in 2021 under Ben Recht and Michael I. Jordan, and his work has
been recognized with an ICML 2018 Best Paper Award, ICML 2022 Outstanding
Paper Award, and RSS 2023 Best Paper Finalist designation.

3:30pm - Pre-talk meet and greet teatime - 219 Prospect Street, 13 floor,
there will be light snacks and beverages in the kitchen area.

 

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.yale.edu/pipermail/sds-seminars/attachments/20240129/90d90573/attachment.html>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: image001.jpg
Type: image/jpeg
Size: 2925 bytes
Desc: not available
URL: <http://mailman.yale.edu/pipermail/sds-seminars/attachments/20240129/90d90573/attachment.jpg>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: image002.jpg
Type: image/jpeg
Size: 13318 bytes
Desc: not available
URL: <http://mailman.yale.edu/pipermail/sds-seminars/attachments/20240129/90d90573/attachment-0001.jpg>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: image004.jpg
Type: image/jpeg
Size: 3820 bytes
Desc: not available
URL: <http://mailman.yale.edu/pipermail/sds-seminars/attachments/20240129/90d90573/attachment-0002.jpg>