<div dir="ltr"><div class="gmail_default" style="font-family:georgia,serif;font-size:small"><div class="gmail_default"><div class="gmail_default"><span style="letter-spacing:0.2px;white-space:pre-wrap"><font face="georgia, serif" color="#000000"><b>When:    </b>Friday, January 27th<b> at <span style="background-color:rgb(255,255,0)">11 AM CT</span></b></font></span></div><div class="gmail_default"><b style="letter-spacing:0.2px;white-space:pre-wrap"><font face="georgia, serif" color="#000000"><br></font></b></div><div class="gmail_default"><font face="georgia, serif" color="#000000"><b style="letter-spacing:0.2px;white-space:pre-wrap">Where:   </b>Talk will be given<span style="background-color:rgb(255,255,0)"> </span><span style="background-color:rgb(255,255,0)"><font style="font-weight:bold"><u>live, in-person</u></font><font style="font-weight:bold"> </font></span>at</font></div><p class="MsoNormal" style="margin:0in;line-height:normal;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><font color="#000000" face="georgia, serif">                   TTIC, 6045 S. Kenwood Avenue</font></p><p class="MsoNormal" style="margin:0in;line-height:normal;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><font color="#000000" face="georgia, serif">                   5th Floor, Room 530<b>  </b></font></p><p class="MsoNormal" style="margin:0in;line-height:normal;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><b style="letter-spacing:0.2px;white-space:pre-wrap"><font color="#000000"><br></font></b></p><p class="MsoNormal" style="margin:0in;line-height:normal;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><font color="#000000"><b style="letter-spacing:0.2px;white-space:pre-wrap">Virtually: </b><span style="letter-spacing:0.2px;white-space:pre-wrap">via Panopto (</span><a href="https://uchicago.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=e737c92e-7907-49cc-8f72-af8e0114571d" style="letter-spacing:0.2px;white-space:pre-wrap" target="_blank">Livestream</a><span style="letter-spacing:0.2px;white-space:pre-wrap">)</span><br></font></p><div class="gmail_default"><b style="letter-spacing:0.2px;white-space:pre-wrap"><font face="georgia, serif" color="#000000"><br></font></b></div><div class="gmail_default"><span style="letter-spacing:0.2px;white-space:pre-wrap"><font face="georgia, serif" color="#000000"><b>Who:     </b></font></span>Theodor Misiakiewicz, Stanford University </div><div class="gmail_default"><b style="letter-spacing:0.2px;white-space:pre-wrap"><font face="georgia, serif" color="#000000"><br></font></b></div><div class="gmail_default"><font face="georgia, serif" color="#000000"><b style="letter-spacing:0.2px;white-space:pre-wrap">Title:     </b></font>New statistical and computational phenomena from Deep Learning<font face="georgia, serif" color="#000000"><br style="letter-spacing:0.2px;white-space:pre-wrap"><b><br style="letter-spacing:0.2px;white-space:pre-wrap"></b></font><b>Abstract:  </b>Deep learning methodology has presented major challenges for statistical learning theory. Indeed deep neural networks often operate in regimes outside the realm of classical statistics and optimization wisdom.  In this talk, we will consider two illustrative examples which clarify some of these new challenges. The first example considers an instance where kernel ridge regression with a simple RBF kernel achieves optimal test error when it perfectly fits the noisy training data. Why can we interpolate noisy data and still generalize well? Why can overfitting be benign in kernel ridge regression? The second example---computational in nature---considers fitting two different smooth ridge functions with deep neural networks (DNNs). Both can be estimated at the same near-parametric rate by DNNs trained with unbounded computational resources. However, empirically, learning becomes much harder for one of these functions when restricted to DNNs trained using SGD. Why does SGD succeed on some functions and fail on others? The goal of this talk will be to understand these two simulations. In particular, we will demonstrate quantitative theories that can precisely capture both phenomena.<br></div><div><font face="georgia, serif" color="#000000"><br></font></div><div><div class="gmail_default"><font face="georgia, serif" color="#000000"><b>Bio: </b></font>Theodor is a sixth-year PhD candidate in Statistics at Stanford University working with Prof. Andrea Montanari. Before his Ph.D, he completed his undergraduate studies in France at Ecole Normale Superieure de Paris with a focus on pure math and physics. He received a B.Sc. in Mathematics and a B.Sc. in Physics in 2014, and a M.Sc. in Theoretical Physics at ICFP in 2016. His interest lies broadly at the intersection of statistics, machine learning, probability, and computer science.</div></div><div class="gmail_default"><br></div><div class="gmail_default">For more information about him and his work, please visit his <a href="https://misiakie.github.io/" target="_blank">personal webpage.</a></div><div class="gmail_default"><br></div><div><div class="gmail_default"><font face="georgia, serif" color="#000000"><b>Host: <a href="mailto:nati@ttic.edu" target="_blank">Nati Srebro</a></b></font></div><font color="#888888"><br style="font-family:Arial,Helvetica,sans-serif"></font></div></div><div style="font-family:Arial,Helvetica,sans-serif"><br></div><div style="font-family:Arial,Helvetica,sans-serif"><br></div><span style="font-family:Arial,Helvetica,sans-serif">--</span><br style="font-family:Arial,Helvetica,sans-serif"><div dir="ltr" style="font-family:Arial,Helvetica,sans-serif"><div dir="ltr"><b><font color="#3d85c6">Brandie Jones </font></b><div><div><div><font color="#3d85c6"><b><i>Executive </i></b></font><b style="color:rgb(61,133,198)"><i>Administrative Assistant</i></b></div></div><div><font color="#3d85c6">Toyota Technological Institute</font></div><div><font color="#3d85c6">6045 S. Kenwood Avenue</font></div><div><font color="#3d85c6">Chicago, IL  60637</font></div></div><div><font color="#3d85c6"><a href="http://www.ttic.edu/" target="_blank">www.ttic.edu</a> </font></div><div><font color="#3d85c6"><div style="background-color:rgb(238,238,238)">Working Remotely on Tuesdays</div></font></div></div></div></div></div>