<html><head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8"><style><!----></style>
<style id="css_styles">
blockquote.cite { margin-left: 5px; margin-right: 0px; padding-left: 10px; padding-right:0px; border-left: 1px solid #cccccc }
blockquote.cite2 {margin-left: 5px; margin-right: 0px; padding-left: 10px; padding-right:0px; border-left: 1px solid #cccccc; margin-top: 3px; padding-top: 0px; }
a img { border: 0px; }
li[style='text-align: center;'], li[style='text-align: center; '], li[style='text-align: right;'], li[style='text-align: right; '] { list-style-position: inside;}
body { font-family: Segoe UI; font-size: 12pt; }
.quote { margin-left: 1em; margin-right: 1em; border-left: 5px #ebebeb solid; padding-left: 0.3em; }
</style>
</head>
<body><div id="x0f22f201515f42e08d49f92d6b1356fd">Welcome to the IDA Machine Learning Seminar on Wednesday, February 24, 15:15 </div><div id="x0f22f201515f42e08d49f92d6b1356fd"><br></div><div id="x0f22f201515f42e08d49f92d6b1356fd"><div><b>Marco Cuturi, </b>Google Brain and CREST - ENSAE, Institut Polytechnique de Paris, France</div><div><a href="https://marcocuturi.net/">https://marcocuturi.net/</a><br><br><div style="background-color:rgba(0,0,0,0);"><b>Differentiating through Optimal Transport</b><br></div><i style="background-color:rgba(0,0,0,0);">Abstract:</i><span> </span><span>Computing or approximating an optimal transport cost is rarely the sole goal when using OT in applications. In most cases this relies instead on approximating that plan (or its application to another vector) to obtain its differentiable properties w.r.t. to its input. I will present in this talk recent applications that highlight this necessity, as well as possible algorithmic and programmatic solutions to handle such issues.</span><span><br></span><div id="x8526749173b04363af82a5b13dbb9924"><div><div><br></div><div><i>Zoom link: </i><a href="https://liu-se.zoom.us/j/69240032654?pwd=UjVKQUhwZ1Y5UFJQYlNtMHB3S21kdz09" style="font-size: 12pt;">https://liu-se.zoom.us/j/69240032654?pwd=UjVKQUhwZ1Y5UFJQYlNtMHB3S21kdz09</a></div><div><i>Meeting ID:</i> 692 4003 2654<br><i>Passcode:</i> 326937</div></div></div></div><div><br></div><div>-------<br>The list of future seminars in the series is available at <a href="http://www.ida.liu.se/research/machinelearning/seminars/">http://www.ida.liu.se/research/machinelearning/seminars/</a>.<br><br></div><div>Welcome!<br>IDA Machine Learning Group</div></div>
</body></html>