<div dir="ltr"><br><br><div class="gmail_quote"><div dir="ltr" class="gmail_attr">---------- Forwarded message ---------<br>From: <strong class="gmail_sendername" dir="auto">Elizavette Torres</strong> <span dir="ltr"><<a href="mailto:elizavette.torres@yale.edu">elizavette.torres@yale.edu</a>></span><br>Date: Fri, Feb 22, 2019 at 9:42 AM<br>Subject: [Statseminars] S&DS Talk, Andrej Risteski, 2/25, "Better understanding of modern paradigms in probabilistic models" DL220<br>To:  <<a href="mailto:Statseminars@mailman.yale.edu">Statseminars@mailman.yale.edu</a>>,  <<a href="mailto:sds-majors@mailman.yale.edu">sds-majors@mailman.yale.edu</a>><br></div><br><br><div lang="EN-US" link="#0563C1" vlink="#954F72"><div class="m_639974807740623911WordSection1"><p class="MsoNormal" style="background:white"><a href="https://statistics.yale.edu/" title="Department of Statistics and Data Science
" target="_blank"><span style="font-size:22.0pt;font-family:"Lucida Sans",sans-serif;color:#286dc0;text-decoration:none"><img border="0" width="150" height="49" style="width:1.5625in;height:.5104in" id="m_639974807740623911logo" src="cid:16915f0eaac4ce8e91" alt="Department of Statistics and Data Science
"></span></a><a href="https://statistics.yale.edu/" title="Home" target="_blank"><b><span style="font-size:22.0pt;font-family:"Lucida Sans",sans-serif;color:#286dc0;text-decoration:none">Department of Statistics and Data Science </span></b></a><span style="font-size:22.0pt;font-family:"Lucida Sans",sans-serif;color:#222222"><u></u><u></u></span></p><h1 style="margin-right:0in;margin-bottom:0in;margin-left:0in;margin-bottom:.0001pt;background:white"><span style="font-family:Mallory;color:#003c76;text-transform:uppercase;font-weight:normal">ANDREJ RISTESKI</span><span style="font-size:13.5pt;font-family:Mallory;color:#222222">, <span class="m_639974807740623911odd">MIT</span></span><span style="font-size:13.5pt;font-family:Mallory;color:#222222;font-weight:normal"><u></u><u></u></span></h1><p class="MsoNormal" style="background:white"><b><span style="font-size:15.0pt;font-family:Mallory;color:#222222"><u></u> <u></u></span></b></p><p class="MsoNormal" style="background:white"><u></u><img width="165" height="198" style="width:1.7187in;height:2.0625in" src="cid:16915f0eaad6917eb2" align="left" hspace="12" alt="https://statistics.yale.edu/sites/default/files/styles/user_picture_node/public/photo_math.png?itok=PQooLet-"><u></u><span class="m_639974807740623911fn"><span style="font-size:13.5pt;font-family:Mallory;color:#222222">Date: Monday, February 25, 2019<u></u><u></u></span></span></p><p class="MsoNormal" style="background:white"><span class="m_639974807740623911fn"><span style="font-size:13.5pt;font-family:Mallory;color:#222222">Time: 4:00PM to 5:15PM<u></u><u></u></span></span></p><p class="MsoNormal" style="background:white"><span class="m_639974807740623911fn"><span style="font-size:13.5pt;font-family:Mallory;color:#222222">Location: Dunham Lab </span></span><span class="m_639974807740623911map-icon"><span style="font-size:12.5pt;font-family:Mallory;color:#222222;letter-spacing:.6pt"><a href="http://maps.google.com/?q=10+Hillhouse+Avenue%2C+Room+220%2C+New+Haven%2C+CT%2C+%2C+us" target="_blank"><span style="color:#286dc0">see map</span></a> </span></span><span style="font-size:13.5pt;font-family:Mallory;color:#222222"><u></u><u></u></span></p><p class="MsoNormal" style="background:white"><span style="font-size:13.5pt;font-family:Mallory;color:#222222">10 Hillhouse Avenue, Room 220<u></u><u></u></span></p><p class="MsoNormal" style="background:white"><span class="m_639974807740623911locality"><span style="font-size:13.5pt;font-family:Mallory;color:#222222">New Haven</span></span><span style="font-size:13.5pt;font-family:Mallory;color:#222222">, <span class="m_639974807740623911region">CT</span><u></u><u></u></span></p><p class="MsoNormal" style="background:white"><span style="font-size:13.5pt;font-family:Mallory;color:#222222"><a href="https://math.mit.edu/~risteski/" target="_blank"><span style="font-size:12.0pt;color:#003c76">Website</span></a><u></u><u></u></span></p><p class="MsoNormal" style="background:white"><span style="font-size:13.5pt;font-family:Mallory;color:#222222"><u></u> <u></u></span></p><p class="MsoNormal" style="background:white"><span style="font-size:13.5pt;font-family:Mallory;color:#222222"><u></u> <u></u></span></p><p class="MsoNormal" style="background:white"><span style="font-size:13.5pt;font-family:Mallory;color:#222222"><u></u> <u></u></span></p><p class="MsoNormal" style="background:white"><span style="font-size:13.5pt;font-family:Mallory;color:#222222"><u></u> <u></u></span></p><p class="MsoNormal" style="background:white"><b><span style="font-size:15.0pt;font-family:Mallory;color:#222222">Better understanding of modern paradigms in probabilistic models<u></u><u></u></span></b></p><p class="MsoNormal" style="background:white"><span style="font-size:13.5pt;font-family:Mallory;color:#222222"><u></u> <u></u></span></p><p class="MsoNormal" style="background:white"><b><span style="font-size:13.5pt;font-family:Mallory;color:#222222">Information and Abstract: <u></u><u></u></span></b></p><p style="margin-right:0in;margin-bottom:12.0pt;margin-left:0in;background:white;box-sizing:inherit"><span style="font-size:13.5pt;font-family:Mallory;color:#222222">In recent years, one of the areas of machine learning that has seen the most exciting progress is unsupervised learning, namely learning in the absence of labels or annotation. An integral part of these advances have been complex probabilistic models for high-dimensional data, capturing different types of intricate latent structure. As a consequence, a lot of statistical and algorithmic issues have emerged, stemming both from learning (fitting a model from raw data) and inference (probabilistic queries and sampling from a known model). A common theme is that the models that are used in practice are often intractable in the worst-case (computationally or statistically), yet even simple algorithms are, to borrow from Wigner, unreasonably effective in practice. It thus behooves us to ask why this happens.<u></u><u></u></span></p><p style="margin-right:0in;margin-bottom:12.0pt;margin-left:0in;background:white;box-sizing:inherit"><span style="font-size:13.5pt;font-family:Mallory;color:#222222">I will showcase some of my research addressing this question, in the context of computationally efficient inference using Langevin dynamics in the presence of multimodality, as well as statistical guarantees for learning distributions using GANs (Generative Adversarial Networks). <u></u><u></u></span></p><p style="margin-right:0in;margin-bottom:12.0pt;margin-left:0in;background:white;box-sizing:inherit"><span style="font-size:13.5pt;font-family:Mallory;color:#222222">BIO: Andrej Risteski holds a joint position as the Norbert Wiener fellow at the Institute for Data Science and Statistics (IDSS) and an Instructor of Applied Mathematics at MIT.<u></u><u></u></span></p><p style="margin-right:0in;margin-bottom:12.0pt;margin-left:0in;background:white;box-sizing:inherit"><span style="font-size:13.5pt;font-family:Mallory;color:#222222">Before coming to MIT, he was a PhD student in the Computer Science Department at Princeton University, working under the advisement of Sanjeev Arora. Prior to that he received his B.S.E. degree at Princeton University as well.<u></u><u></u></span></p><p style="margin-right:0in;margin-bottom:12.0pt;margin-left:0in;background:white;box-sizing:inherit"><span style="font-size:13.5pt;font-family:Mallory;color:#222222">His work lies in the intersection of machine learning and theoretical computer science. The broad goal of his research is theoretically understanding statistical and algorithmic phenomena and problems arising in modern machine learning.<u></u><u></u></span></p><p class="MsoNormal" style="line-height:18.0pt;background:white"><span style="font-size:13.5pt;font-family:Mallory;color:#222222"><u></u> <u></u></span></p><p class="MsoNormal" style="line-height:18.0pt;background:white"><a><b><span style="font-size:16.0pt;font-family:Mallory;color:red;text-decoration:none">3:45 p.m.</span></b></a><b><span style="font-size:16.0pt;font-family:Mallory;color:red">   Pre-talk tea Dunham Lab, Suite 222, Breakroom 228<u></u><u></u></span></b></p><p class="MsoNormal" style="background:white;vertical-align:baseline"><span style="font-size:12.0pt;font-family:Mallory">For more details and upcoming events visit our website at </span><a href="http://statistics.yale.edu/" target="_blank"><span style="font-size:12.0pt;font-family:Mallory;color:#0563c1">http://statistics.yale.edu/</span></a><span style="font-size:12.0pt;font-family:Mallory"> .<u></u><u></u></span></p><p class="MsoNormal"><u></u> <u></u></p><p class="MsoNormal"><u></u> <u></u></p><p class="MsoNormal"><u></u> <u></u></p></div></div>_______________________________________________<br>
Statseminars mailing list<br>
<a href="mailto:Statseminars@mailman.yale.edu" target="_blank">Statseminars@mailman.yale.edu</a><br>
<a href="https://mailman.yale.edu/mailman/listinfo/statseminars" rel="noreferrer" target="_blank">https://mailman.yale.edu/mailman/listinfo/statseminars</a><br>
</div></div>