NOW! - Thesis Defense - July 23, 2025 - Youngseog Chung - Methods for Calibrated Uncertainty Quantification and Understanding its Utility

[Jeff Schneider]

Hi Everyone,

This is starting right now in GHC 8102.  Please come and join to hear 
about UQ!

Jeff.




-------- Forwarded Message --------
Subject: 	Reminder - Thesis Defense - July 23, 2025 - Youngseog Chung - 
Methods for Calibrated Uncertainty Quantification and Understanding its 
Utility
Date: 	Wed, 23 Jul 2025 13:32:49 -0400
From: 	Diane L Stidle <stidle at andrew.cmu.edu>
To: 	ml-seminar at cs.cmu.edu <ML-SEMINAR at cs.cmu.edu>, jsnoek at google.com



*/Thesis Defense/*

Date: July 23, 2025 (Wed)
Time: 2:30pm (ET)
Place: GHC 8102 & Remote
PhD Candidate: Youngseog Chung
*
*
*Thesis Title:*
Methods for Calibrated Uncertainty Quantification and Understanding its 
Utility
*
*
*Abstract:*
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.

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.
*
Thesis Committee:*
Jeff Schneider (Chair)
Aarti Singh
Zico Kolter
Jasper Snoek (Google Deepmind)
*
*
*Link to the draft document: *
https://youngseogchung.github.io/docs/Thesis.pdf

*Zoom meeting link:*
https://cmu.zoom.us/j/99486342780?pwd=HQOzBqHgdHLLDbbQonw0nbgV4ngvQy.1&jst=2 
<https://cmu.zoom.us/j/99486342780?pwd=HQOzBqHgdHLLDbbQonw0nbgV4ngvQy.1&jst=2>



-- 
-- 
Diane Stidle
PhD Program Manager
Machine Learning Department
Carnegie Mellon University
diane at cs.cmu.edu
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/autonlab-users/attachments/20250723/a649082a/attachment.html>