<!DOCTYPE html>
<html>
<head>
<meta http-equiv="content-type" content="text/html; charset=UTF-8">
</head>
<body>
<p>Hi Everyone,</p>
<p>This is starting right now in GHC 8102. Please come and join to
hear about UQ!</p>
<p>Jeff.</p>
<p><br>
</p>
<div class="moz-forward-container"><br>
<br>
-------- Forwarded Message --------
<table cellpadding="0" cellspacing="0" border="0"
class="moz-email-headers-table">
<tbody>
<tr>
<th valign="BASELINE" align="RIGHT" nowrap="nowrap">Subject:
</th>
<td>Reminder - Thesis Defense - July 23, 2025 - Youngseog
Chung - Methods for Calibrated Uncertainty Quantification
and Understanding its Utility</td>
</tr>
<tr>
<th valign="BASELINE" align="RIGHT" nowrap="nowrap">Date: </th>
<td>Wed, 23 Jul 2025 13:32:49 -0400</td>
</tr>
<tr>
<th valign="BASELINE" align="RIGHT" nowrap="nowrap">From: </th>
<td>Diane L Stidle <a class="moz-txt-link-rfc2396E" href="mailto:stidle@andrew.cmu.edu"><stidle@andrew.cmu.edu></a></td>
</tr>
<tr>
<th valign="BASELINE" align="RIGHT" nowrap="nowrap">To: </th>
<td><a class="moz-txt-link-abbreviated" href="mailto:ml-seminar@cs.cmu.edu">ml-seminar@cs.cmu.edu</a> <a class="moz-txt-link-rfc2396E" href="mailto:ML-SEMINAR@cs.cmu.edu"><ML-SEMINAR@cs.cmu.edu></a>,
<a class="moz-txt-link-abbreviated" href="mailto:jsnoek@google.com">jsnoek@google.com</a></td>
</tr>
</tbody>
</table>
<br>
<br>
<meta http-equiv="content-type" content="text/html; charset=UTF-8">
<div dir="ltr">
<div>
<div dir="ltr">
<div>
<div><b><i>Thesis Defense</i></b></div>
<div><br>
</div>
<div>
<div>Date: July 23, 2025 (Wed)<br>
</div>
<div>Time: 2:30pm (ET)<br>
</div>
<div>Place: GHC 8102 & Remote<br>
</div>
<div>PhD Candidate: Youngseog Chung</div>
</div>
<div>
<div><b><br>
</b></div>
<div><b>Thesis Title:</b><br>
Methods for Calibrated Uncertainty Quantification and
Understanding its Utility<br>
</div>
<div><b><br>
</b></div>
<div><b>Abstract:</b> </div>
<div>As machine learning models have become more capable
of dealing with complex data, they have been entrusted
with an increasing array of predictive tasks. With
such growing reliance on model predictions, being able
to assess whether a given model prediction is reliable
has become equally important. Uncertainty
quantification (UQ) plays a critical role in this
context by providing a measure of confidence in a
model's predictions. In this thesis, I address the
problem of UQ in machine learning in three different
stages.<br>
<br>
</div>
<div>The first section presents an overview of
evaluation in UQ and an open-source software which
provides various utilities in evaluating, visualizing,
and recalibrating predictive uncertainty. The second
section discusses algorithms designed to produce
well-calibrated predictive uncertainties in regression
models, which output a distribution over
continuous-valued outputs. The first work in this
section presents a suite of algorithms for training
univariate probabilistic regression models, and the
second work discusses an extension to the multivariate
setting. The third section presents the utilization of
predictive uncertainties in the decision-making
setting. The application setting dictates how the
uncertainties will be used, and I present a collection
of works which utilizes uncertainties in the
single-step decision making setting, sequential
decision-making setting, and in model-based
reinforcement learning.</div>
<div><b><br>
Thesis Committee:</b></div>
<div>Jeff Schneider (Chair) </div>
<div>Aarti Singh</div>
<div>Zico Kolter </div>
<div>Jasper Snoek (Google Deepmind)</div>
<div><b><br>
</b></div>
<div><b>Link to the draft document: </b></div>
<div><a
href="https://youngseogchung.github.io/docs/Thesis.pdf" target="_blank"
moz-do-not-send="true" class="moz-txt-link-freetext">https://youngseogchung.github.io/docs/Thesis.pdf</a><br>
</div>
<div><br>
</div>
<div><b>Zoom meeting link:</b> </div>
<div><a
href="https://cmu.zoom.us/j/99486342780?pwd=HQOzBqHgdHLLDbbQonw0nbgV4ngvQy.1&jst=2"
target="_blank" moz-do-not-send="true">https://cmu.zoom.us/j/99486342780?pwd=HQOzBqHgdHLLDbbQonw0nbgV4ngvQy.1&jst=2</a></div>
</div>
</div>
</div>
<div dir="ltr"><br>
</div>
<br clear="all">
</div>
<br>
<span class="gmail_signature_prefix">-- </span><br>
<div dir="ltr" class="gmail_signature"
data-smartmail="gmail_signature">
<div dir="ltr"><span>-- </span><br>
<div>Diane Stidle <br>
PhD Program Manager <br>
Machine Learning Department <br>
Carnegie Mellon University <br>
<a href="mailto:diane@cs.cmu.edu" target="_blank"
moz-do-not-send="true" class="moz-txt-link-freetext">diane@cs.cmu.edu</a></div>
</div>
</div>
</div>
</div>
</body>
</html>