<html aria-label="message body">
<head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
</head>
<body style="overflow-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;">
<div>ETH Foundations of Data Science (ETH-FDS), in association with ETH AI Center, announces and invites you to the following talk in our seminar series:</div>
<div><br>
</div>
<div>„Particle Dynamics and Dimensionality Reduction“</div>
<div><br>
</div>
<div>by <span style="font-weight: bold;">Stefan Steinerberger, UW Seattle</span></div>
<div><br>
</div>
<div><b>Date and Time (Zurich): Monday, 11 May 2026, 17:15 - 18.15</b></div>
<div><b>Place: <span class="Apple-tab-span" style="white-space:pre"> </span>
HG F 3</b></div>
<div><br>
</div>
<div><b>Abstract</b>: Dimensionality reduction, moving data from very high dimensions to intermediate dimensions, is well-established. It is not too difficult to accurately map n points into ~log(n) dimensions. The problem becomes a lot more difficult if one
insists that the high-dimensional data be embedded into 2 dimensions which is what researchers in the biomedical fields need. Moreover, there are algorithms (most prominently tSNE and UMAP) that "semi-successfully" do this: they tend to work (though they also
tend to fail on very simple examples). An added difficulty is that it is difficult to assess from the output when they work. I will argue that these algorithms reduce to understanding an attraction-repulsion functional acting on a large number of particles;
this viewpoint immediately suggests new ideas and algorithms as well as a few benchmark problems.</div>
<div><br>
</div>
<div>Seminar websites: https://math.ethz.ch/sfs/news-and-events/data-science-seminar.html, https://math.ethz.ch/sfs/eth-foundations-of-data-science.html</div>
<div><br>
</div>
<div>Organisers: A. Bandeira, H. Bölcskei, P. Bühlmann, J. Peters, F. Yang</div>
<div><br>
</div>
</body>
</html>