<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 class="elementToProof" id="WACViewPanel_ClipboardElement">
<h1 style="direction: ltr; text-align: left; text-indent: 0px; margin-top: 12pt; margin-right: 0px; margin-left: 0px; font-family: "Aptos Display"; font-size: 16pt; font-weight: normal; color: rgb(24, 90, 189);" class="elementToProof">
Welcome to an IDA Machine Learning Seminar on Wednesday, September 10 at 13:30 in Alan Turing</h1>
<div style="direction: ltr; text-align: left; text-indent: 0px; margin: 0px 0px 10.6667px; font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);" class="elementToProof">
<b>SDE Matching: Scalable Variational Inference for Stochastic Differential Equations</b></div>
<div style="direction: ltr; text-align: left; text-indent: 0px; margin: 0px 0px 10.6667px; font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);" class="elementToProof">
<b><a title="https://naesseth.github.io/" class="OWAAutoLink" id="LPlnk921655" href="https://naesseth.github.io/">Christian Naesseth</a>, University of Amsterdam</b></div>
<div class="_Entity _EType_OWALinkPreview _EId_OWALinkPreview _EReadonly_1" style="width:100%;display:inline-block">
<div id="LPBorder_GTaHR0cHM6Ly9uYWVzc2V0aC5naXRodWIuaW8v" class="LPBorder579919" style="width:100%;margin-top:16px;margin-bottom:16px;max-width:800px;min-width:424px">
<table id="LPContainer579919" style="padding:12px 36px 12px 12px;width:100%;border-width:1px;border-style:solid;border-color:rgb(200, 200, 200);border-radius:2px">
<tbody>
<tr valign="top" style="border-spacing:0px">
<td style="width:100%">
<div id="LPTitle579919" style="font-size:21px;font-weight:300;margin-right:8px;font-family:wf_segoe-ui_light, "Segoe UI Light", "Segoe WP Light", "Segoe UI", "Segoe WP", Tahoma, Arial, sans-serif;margin-bottom:12px">
<a target="_blank" id="LPUrlAnchor579919" href="https://naesseth.github.io/" style="text-decoration:none">Elemental AI | Christian A. Naesseth</a></div>
<div id="LPDescription579919" style="font-size:14px;max-height:100px;color:rgb(102, 102, 102);font-family:wf_segoe-ui_normal, "Segoe UI", "Segoe WP", Tahoma, Arial, sans-serif;margin-bottom:12px;margin-right:8px;overflow:hidden">
CAN Lab, Informatics Institute, University of AmsterdamI am an Assistant Professor of Machine Learning at the University of Amsterdam, a member of the Amsterdam Machine Learning Lab, the lab manager of the UvA-Bosch Delta Lab 2, and an ELLIS member. My research
interests span generative modeling, uncertainty quantification, reasoning, and machine learning, as well as their application to the ...</div>
<div id="LPMetadata579919" style="font-size:14px;color:rgb(166, 166, 166);font-family:wf_segoe-ui_normal, "Segoe UI", "Segoe WP", Tahoma, Arial, sans-serif">
naesseth.github.io</div>
</td>
</tr>
</tbody>
</table>
</div>
</div>
<div style="direction: ltr; text-align: left; text-indent: 0px; margin: 0px 0px 10.6667px; font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);" class="elementToProof">
<i>Abstract:</i> The Latent Stochastic Differential Equation (SDE) is a powerful tool for time series and sequence modeling. However, training Latent SDEs typically relies on adjoint sensitivity methods, which depend on simulation, discretisation, and backpropagation
through approximate SDE solutions, which limit scalability. In this work, we propose SDE Matching, a new simulation- and discretisation-free method for training Latent SDEs. Inspired by modern Score- and Flow Matching algorithms for learning generative dynamics,
we extend these ideas to the domain of stochastic dynamics for time series and sequence modeling, eliminating the need for costly numerical simulations. Our results demonstrate that SDE Matching achieves performance comparable to adjoint sensitivity methods
while drastically reducing computational complexity.</div>
<div style="direction: ltr; text-align: left; text-indent: 0px; margin: 0px 0px 10.6667px; font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt;" class="elementToProof">
<span style="color: rgb(0, 0, 0);">Location: <b>Alan Turing,</b> </span><span style="color: rgb(70, 120, 134);"><u><a style="color: rgb(70, 120, 134);" rel="noreferrer noopener" class="Hyperlink SCXW237411067 BCX2 OWAAutoLink" id="OWAbaf874be-ee15-9f32-44dd-012ce3808530" target="_blank" href="https://www.ida.liu.se/department/location/search.en.shtml?keyword=alan">https://www.ida.liu.se/department/location/search.en.shtml?keyword=alan</a></u></span><span style="color: rgb(0, 0, 0);"> </span></div>
<div style="direction: ltr; text-align: left; text-indent: 0px; margin: 0px 0px 10.6667px; font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);" class="elementToProof">
</div>
<div style="direction: ltr; text-align: left; text-indent: 0px; margin: 0px 0px 10.6667px; font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);" class="elementToProof">
------------------ </div>
<div style="direction: ltr; text-align: left; text-indent: 0px; margin: 0px 0px 10.6667px; font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt;" class="elementToProof">
<span style="color: rgb(0, 0, 0);">The list of future seminars in the series is available at: <br>
</span><span style="color: rgb(70, 120, 134);"><u><a style="color: rgb(70, 120, 134);" rel="noreferrer noopener" class="Hyperlink SCXW237411067 BCX2 OWAAutoLink" id="OWAd8f80309-ecdb-5cdc-4523-6c4c57388171" target="_blank" href="https://stima.gitlab-pages.liu.se/ml-seminars/">https://stima.gitlab-pages.liu.se/ml-seminars/</a></u></span><span style="color: rgb(0, 0, 0);"> </span></div>
<div style="direction: ltr; text-align: left; text-indent: 0px; margin: 0px 0px 10.6667px; font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt;" class="elementToProof">
<span style="color: rgb(0, 0, 0);">You can subscribe to the seminar series' calendar using this ics link:
</span><span style="color: rgb(70, 120, 134);"><u><a style="color: rgb(70, 120, 134);" rel="noreferrer noopener" class="Hyperlink SCXW237411067 BCX2 OWAAutoLink" id="OWA8cc2fc41-a68c-3364-0f27-cbf91ee3fd60" target="_blank" href="https://outlook.office365.com/owa/calendar/4d811ae47ce446f58d11a7c2f50a7ed8@ad.liu.se/0f5253d7bc7841248c71eb4c28eb2d668927992292494627279/calendar.ics">https://outlook.office365.com/owa/calendar/4d811ae47ce446f58d11a7c2f50a7ed8@ad.liu.se/0f5253d7bc7841248c71eb4c28eb2d668927992292494627279/calendar.ics</a></u></span><span style="color: rgb(0, 0, 0);"> </span></div>
</div>
<div style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);" class="elementToProof">
<br>
</div>
<div class="elementToProof" id="Signature">
<div style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);" class="elementToProof">
<br>
</div>
<div style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);" class="elementToProof">
--</div>
<div style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);" class="elementToProof">
<b>Louis Ohl</b></div>
<div style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 11pt; color: rgb(0, 0, 0);" class="elementToProof">
Postdoc</div>
<div style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 11pt; color: rgb(0, 0, 0);" class="elementToProof">
louis.ohl@liu.se</div>
<div style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);" class="elementToProof">
<br>
</div>
<div style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);" class="elementToProof">
<b>Linköping University</b></div>
<div style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 11pt; color: rgb(0, 0, 0);" class="elementToProof">
IDA / STIMA</div>
<div style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 11pt; color: rgb(0, 0, 0);" class="elementToProof">
B-Huset, 2A:445</div>
<div style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 11pt; color: rgb(0, 0, 0);" class="elementToProof">
<a title="https://oshillou.github.io/" class="OWAAutoLink" id="OWA25e6351f-e331-53ae-4cac-fd07dd93b4d2" href="https://oshillou.github.io/">Webpage</a></div>
</div>
</body>
</html>