[Colloquium] Reminder - Ruoxi Jiang MS Presentation/Aug 14, 2023

[Megan Woodward]

This is an announcement of Ruoxi Jiang's MS Presentation
===============================================
Candidate: Ruoxi Jiang

Date: Monday, August 14, 2023

Time: 10 am CST

Location: JCL 298

M.S. Paper Title: EMBED AND EMULATE: LEARNING TO ESTIMATE PARAMETERS OF DYNAMICAL SYSTEMS WITH UNCERTAINTY QUANTIFICATION

Abstract: In this talk, I am going to discuss how to leverage structural hidden representations of dynamical systems to address inverse problems with uncertainty quantification. In particular, we explore learning emulators for parameter estimation of high-dimensional dynamical systems. We assume access to a computationally complex simulator that inputs a candidate parameter and outputs a corresponding multichannel time series. Our task is to accurately estimate a range of likely values of the underlying parameters.
Standard iterative approaches necessitate running the simulator many times, which is computationally prohibitive. To address this challenge, we will describe a novel framework for learning feature embeddings of observed dynamics jointly with an emulator that can replace high-cost simulators for parameter estimation. Leveraging a contrastive learning approach, our method exploits intrinsic data properties within and across parameter and trajectory domains. On a coupled 396-dimensional multiscale Lorenz 96 system, our method significantly outperforms a typical parameter estimation method based on predefined metrics and a classical numerical simulator, and with only 1.19% of the baseline's computation time. Ablation studies highlight the potential of explicitly designing learned emulators for parameter estimation by leveraging contrastive learning.

Advisors: Rebecca Willett

Committee Members: Rebecca Willett, Michael Maire, and Yuxin Chen
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.cs.uchicago.edu/pipermail/colloquium/attachments/20230814/e53ccd0c/attachment-0001.html>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: master thesis-ruoxi jiang.pdf
Type: application/pdf
Size: 1425281 bytes
Desc: master thesis-ruoxi jiang.pdf
URL: <http://mailman.cs.uchicago.edu/pipermail/colloquium/attachments/20230814/e53ccd0c/attachment-0001.pdf>