<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=iso-8859-1">
<style type="text/css" style="display:none;"> P {margin-top:0;margin-bottom:0;} </style>
</head>
<body dir="ltr">
<div style="font-family: Calibri, Helvetica, sans-serif; font-size: 11pt; color: rgb(0, 0, 0);" class="elementToProof">
<span class="ContentPasted0" style="orphans:auto;widows:auto;text-decoration:none;font-family:Helvetica;font-size:12px;display:inline !important">This is an announcement of Ruoxi Jiang's MS Presentation</span><br class="ContentPasted0" style="orphans:auto;widows:auto;text-decoration:none;font-family:Helvetica;font-size:12px">
<span class="ContentPasted0" style="orphans:auto;widows:auto;text-decoration:none;font-family:Helvetica;font-size:12px;display:inline !important">===============================================</span><br class="ContentPasted0" style="orphans:auto;widows:auto;text-decoration:none;font-family:Helvetica;font-size:12px">
<span class="ContentPasted0" style="orphans:auto;widows:auto;text-decoration:none;font-family:Helvetica;font-size:12px;display:inline !important">Candidate: Ruoxi Jiang</span><br class="ContentPasted0" style="orphans:auto;widows:auto;text-decoration:none;font-family:Helvetica;font-size:12px">
<br class="ContentPasted0" style="orphans:auto;widows:auto;text-decoration:none;font-family:Helvetica;font-size:12px">
<span class="ContentPasted0" style="orphans:auto;widows:auto;text-decoration:none;font-family:Helvetica;font-size:12px;display:inline !important">Date: Monday, August 14, 2023</span><br class="ContentPasted0" style="orphans:auto;widows:auto;text-decoration:none;font-family:Helvetica;font-size:12px">
<br class="ContentPasted0" style="orphans:auto;widows:auto;text-decoration:none;font-family:Helvetica;font-size:12px">
<span class="ContentPasted0" style="orphans:auto;widows:auto;text-decoration:none;font-family:Helvetica;font-size:12px;display:inline !important">Time: 10 am CST</span><br class="ContentPasted0" style="orphans:auto;widows:auto;text-decoration:none;font-family:Helvetica;font-size:12px">
<br class="ContentPasted0" style="orphans:auto;widows:auto;text-decoration:none;font-family:Helvetica;font-size:12px">
<span class="ContentPasted0" style="orphans:auto;widows:auto;text-decoration:none;font-family:Helvetica;font-size:12px;display:inline !important">Location: JCL 298</span><br class="ContentPasted0" style="orphans:auto;widows:auto;text-decoration:none;font-family:Helvetica;font-size:12px">
<br class="ContentPasted0" style="orphans:auto;widows:auto;text-decoration:none;font-family:Helvetica;font-size:12px">
<span class="ContentPasted0" style="orphans:auto;widows:auto;text-decoration:none;font-family:Helvetica;font-size:12px;display:inline !important">M.S. Paper Title: EMBED AND EMULATE: LEARNING TO ESTIMATE PARAMETERS OF DYNAMICAL SYSTEMS WITH UNCERTAINTY QUANTIFICATION</span><br class="ContentPasted0" style="orphans:auto;widows:auto;text-decoration:none;font-family:Helvetica;font-size:12px">
<br class="ContentPasted0" style="orphans:auto;widows:auto;text-decoration:none;font-family:Helvetica;font-size:12px">
<span class="ContentPasted0" style="orphans:auto;widows:auto;text-decoration:none;font-family:Helvetica;font-size:12px;display:inline !important">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.<span class="Apple-converted-space ContentPasted0"> </span></span><br class="ContentPasted0" style="orphans:auto;widows:auto;text-decoration:none;font-family:Helvetica;font-size:12px">
<span class="ContentPasted0" style="orphans:auto;widows:auto;text-decoration:none;font-family:Helvetica;font-size:12px;display:inline !important">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.</span><br class="ContentPasted0" style="orphans:auto;widows:auto;text-decoration:none;font-family:Helvetica;font-size:12px">
<br class="ContentPasted0" style="orphans:auto;widows:auto;text-decoration:none;font-family:Helvetica;font-size:12px">
<span class="ContentPasted0" style="orphans:auto;widows:auto;text-decoration:none;font-family:Helvetica;font-size:12px;display:inline !important">Advisors: Rebecca Willett</span><br class="ContentPasted0" style="orphans:auto;widows:auto;text-decoration:none;font-family:Helvetica;font-size:12px">
<br class="ContentPasted0" style="orphans:auto;widows:auto;text-decoration:none;font-family:Helvetica;font-size:12px">
<span class="ContentPasted0" style="orphans:auto;widows:auto;text-decoration:none;font-family:Helvetica;font-size:12px;display:inline !important">Committee Members: Rebecca Willett, Michael Maire, and Yuxin Chen</span><br>
</div>
</body>
</html>