[CMU AI Seminar] Fwd: Mar 2 (Zoom) -- Vaishnavh Nagarajan (CMU) -- Understanding the Failure Modes of Out-of-Distribution Generalization -- AI Seminar sponsored by Fortive

[Shaojie Bai]

Hi all,

Just a reminder that the CMU AI Seminar <http://www.cs.cmu.edu/~aiseminar/> is
tomorrow 12pm-1pm:
https://cmu.zoom.us/j/94477694788?pwd=WmdvNTlsUW5oRHl1dFRDbzkrVmVNdz09.

Vaishnavh Nagarajan (CMU) will be talking about the theories and intuitions
behind the failure modes of out-of-distribution generalization (see below).

Thanks,
Shaojie

---------- Forwarded message ---------
From: Shaojie Bai <shaojieb at andrew.cmu.edu>
Date: Tue, Feb 23, 2021 at 12:15 PM
Subject: Mar 2 (Zoom) -- Vaishnavh Nagarajan (CMU) -- Understanding the
Failure Modes of Out-of-Distribution Generalization -- AI Seminar sponsored
by Fortive
To: <ai-seminar-announce at cs.cmu.edu>


Dear all,

We look forward to seeing you *next Tuesday (3/2)* from 12:00-1:00 PM (U.S.
Eastern time) for the next talk of our *CMU AI seminar*, sponsored by
Fortive <https://careers.fortive.com/>.

To learn more about the seminar series, see the future schedule, or add the
seminar calendar to your own, please visit the seminar website
<http://www.cs.cmu.edu/~aiseminar/>. <http://www.cs.cmu.edu/~aiseminar/>

On 3/2, *Vaishnavh Nagarajan* (CMU Computer Science Department) will be
giving a talk on "*Understanding the Failure Modes of Out-of-Distribution
Generalization*."

*Title*: Understanding the Failure Modes of Out-of-Distribution
Generalization

*Talk Abstract*: Classifiers often rely on features like the background
that may be spuriously correlated with the label. In practice, this results
in poor test-time accuracy as the classifier may be deployed in an
environment where these spurious correlations no longer hold. While many
algorithms have been developed to heuristically tackle this challenge of
out-of-distribution generalization, in this work, we take a step back to
ask: why do classifiers rely on spurious correlations in the first place?
While the answer to this might seem straightforward, I'll begin by
explaining why existing theoretical models of spurious correlations do not
capture the fundamental reasons behind why classifiers rely on spurious
correlations. I'll then propose an alternative theoretical model which
helps uncover those fundamental reasons. In particular, by theoretically
studying linear classifiers in this theoretical model, we'll look at two
failure modes: one that is "geometric" in nature another that is
"statistical" in nature. These modes shed insight to the exact biases in
gradient descent, and the exact properties of real-world data that
incentivize classifiers to use spurious correlations. Finally, I'll discuss
experiments on neural networks that validate these insights in more
practical scenarios. Hopefully, with the knowledge of these failure modes,
algorithm designers can be better informed about how to fix these failure
modes, and OoD research can be built upon a more rigorous foundation.

*Speaker Bio*: Vaishnavh Nagarajan is a final year Computer Science PhD
student at Carnegie Mellon University (CMU), advised by Zico Kolter.
Vaishnavh is broadly interested in the theoretical foundations of machine
learning, involving problems in the intersection of learning theory and
optimization. He is particularly interested in theoretically understanding
when and why modern machine learning algorithms work (or do not work) in
practice. His work has received an Outstanding New Directions Paper Award
at NeurIPS'19, an oral presentation at NeurIPS'17 and three workshop
spotlight talks. Prior to CMU, Vaishnavh completed his undergraduate
studies in Computer Science and Engineering in the Indian Institute of
Technology, Madras.

*Zoom Link*:
https://cmu.zoom.us/j/94477694788?pwd=WmdvNTlsUW5oRHl1dFRDbzkrVmVNdz09


Thanks,
Shaojie Bai (MLD)
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/ai-seminar-announce/attachments/20210301/9eda43e8/attachment.html>