<html xmlns:v="urn:schemas-microsoft-com:vml" xmlns:o="urn:schemas-microsoft-com:office:office" xmlns:w="urn:schemas-microsoft-com:office:word" xmlns:m="http://schemas.microsoft.com/office/2004/12/omml" xmlns="http://www.w3.org/TR/REC-html40"><head><META HTTP-EQUIV="Content-Type" CONTENT="text/html; charset=us-ascii"><meta name=Generator content="Microsoft Word 15 (filtered medium)"><!--[if !mso]><style>v\:* {behavior:url(#default#VML);}
o\:* {behavior:url(#default#VML);}
w\:* {behavior:url(#default#VML);}
.shape {behavior:url(#default#VML);}
</style><![endif]--><style><!--
/* Font Definitions */
@font-face
{font-family:"Cambria Math";
panose-1:2 4 5 3 5 4 6 3 2 4;}
@font-face
{font-family:Calibri;
panose-1:2 15 5 2 2 2 4 3 2 4;}
/* Style Definitions */
p.MsoNormal, li.MsoNormal, div.MsoNormal
{margin:0in;
font-size:11.0pt;
font-family:"Calibri",sans-serif;}
h1
{mso-style-priority:9;
mso-style-link:"Heading 1 Char";
mso-margin-top-alt:auto;
margin-right:0in;
mso-margin-bottom-alt:auto;
margin-left:0in;
font-size:24.0pt;
font-family:"Calibri",sans-serif;
font-weight:bold;}
h2
{mso-style-priority:9;
mso-style-link:"Heading 2 Char";
mso-margin-top-alt:auto;
margin-right:0in;
mso-margin-bottom-alt:auto;
margin-left:0in;
font-size:18.0pt;
font-family:"Calibri",sans-serif;
font-weight:bold;}
a:link, span.MsoHyperlink
{mso-style-priority:99;
color:#0563C1;
text-decoration:underline;}
span.Heading1Char
{mso-style-name:"Heading 1 Char";
mso-style-priority:9;
mso-style-link:"Heading 1";
font-family:"Calibri",sans-serif;
font-weight:bold;}
span.Heading2Char
{mso-style-name:"Heading 2 Char";
mso-style-priority:9;
mso-style-link:"Heading 2";
font-family:"Calibri",sans-serif;
font-weight:bold;}
span.odd
{mso-style-name:odd;}
span.date-display-single
{mso-style-name:date-display-single;}
span.date-display-range
{mso-style-name:date-display-range;}
span.date-display-start
{mso-style-name:date-display-start;}
span.date-display-end
{mso-style-name:date-display-end;}
span.fn
{mso-style-name:fn;}
span.map-icon
{mso-style-name:map-icon;}
span.locality
{mso-style-name:locality;}
span.region
{mso-style-name:region;}
span.postal-code
{mso-style-name:postal-code;}
.MsoChpDefault
{mso-style-type:export-only;
font-size:10.0pt;}
@page WordSection1
{size:8.5in 11.0in;
margin:1.0in 1.0in 1.0in 1.0in;}
div.WordSection1
{page:WordSection1;}
--></style><!--[if gte mso 9]><xml>
<o:shapedefaults v:ext="edit" spidmax="1027" />
</xml><![endif]--><!--[if gte mso 9]><xml>
<o:shapelayout v:ext="edit">
<o:idmap v:ext="edit" data="1" />
</o:shapelayout></xml><![endif]--></head><body lang=EN-US link="#0563C1" vlink="#954F72" style='word-wrap:break-word'><div class=WordSection1><p class=MsoNormal style='background:white'><span style='color:black'><a href="https://statistics.yale.edu/" title="Department of Statistics and Data Science
"><span style='font-size:22.0pt;font-family:"Arial",sans-serif;color:#286DC0;text-decoration:none'><img border=0 width=150 height=49 style='width:1.5625in;height:.5104in' id=logo src="cid:image001.jpg@01D93C66.7AD8F570" alt="Department of Statistics and Data Science
"></span></a></span><span style='font-family:"Arial",sans-serif;color:black'> <a href="https://statistics.yale.edu/" title=Home><b><span style='font-size:22.0pt;color:#286DC0'>Department of Statistics and Data Science </span></b></a></span><b><i><u><span style='font-size:22.0pt;font-family:"Arial",sans-serif;color:#286DC0'> <o:p></o:p></span></u></i></b></p><p style='margin:0in'><strong><span style='font-family:"Arial",sans-serif;font-weight:normal'>In-Person seminars will be held at Mason Lab 211, 9 Hillhouse Avenue with the option of virtual participation (</span></strong><span style='font-family:"Arial",sans-serif'><a href="https://yale.hosted.panopto.com/Panopto/Pages/Sessions/List.aspx?folderID=f8b73c34-a27b-42a7-a073-af2d00f90ffa"><span style='color:windowtext;text-decoration:none'>https://yale.hosted.panopto.com/Panopto/Pages/Sessions/List.aspx?folderID=f8b73c34-a27b-42a7-a073-af2d00f90ffa</span></a>)<o:p></o:p></span></p><p class=MsoNormal style='box-sizing: inherit'><strong><span style='font-family:"Arial",sans-serif;font-weight:normal'><a href="https://0.0.0.10/"><span style='color:windowtext;text-decoration:none'>3:30pm</span></a> - Pre-talk meet and greet teatime - Dana House, 24 Hillhouse Avenue </span></strong><strong><span style='font-family:"Calibri",sans-serif;font-weight:normal'><o:p></o:p></span></strong></p><p class=MsoNormal><strong><span style='font-family:"Arial",sans-serif;font-weight:normal'><o:p> </o:p></span></strong></p><h1 style='margin:0in'><span style='font-size:14.0pt;font-family:"Arial",sans-serif'>Matus Jan Telgarsky, <span class=odd>University of Illinois Urbana-Champaign</span></span><span style='font-size:14.0pt'><o:p></o:p></span></h1><p class=MsoNormal><!--[if gte vml 1]><v:shapetype id="_x0000_t75" coordsize="21600,21600" o:spt="75" o:preferrelative="t" path="m@4@5l@4@11@9@11@9@5xe" filled="f" stroked="f">
<v:stroke joinstyle="miter" />
<v:formulas>
<v:f eqn="if lineDrawn pixelLineWidth 0" />
<v:f eqn="sum @0 1 0" />
<v:f eqn="sum 0 0 @1" />
<v:f eqn="prod @2 1 2" />
<v:f eqn="prod @3 21600 pixelWidth" />
<v:f eqn="prod @3 21600 pixelHeight" />
<v:f eqn="sum @0 0 1" />
<v:f eqn="prod @6 1 2" />
<v:f eqn="prod @7 21600 pixelWidth" />
<v:f eqn="sum @8 21600 0" />
<v:f eqn="prod @7 21600 pixelHeight" />
<v:f eqn="sum @10 21600 0" />
</v:formulas>
<v:path o:extrusionok="f" gradientshapeok="t" o:connecttype="rect" />
<o:lock v:ext="edit" aspectratio="t" />
</v:shapetype><v:shape id="Picture_x0020_3" o:spid="_x0000_s1026" type="#_x0000_t75" style='position:absolute;margin-left:0;margin-top:.25pt;width:111.25pt;height:133.5pt;z-index:251658240;visibility:visible;mso-wrap-style:square;mso-width-percent:0;mso-height-percent:0;mso-wrap-distance-left:9pt;mso-wrap-distance-top:0;mso-wrap-distance-right:9pt;mso-wrap-distance-bottom:0;mso-position-horizontal:absolute;mso-position-horizontal-relative:text;mso-position-vertical:absolute;mso-position-vertical-relative:text;mso-width-percent:0;mso-height-percent:0;mso-width-relative:page;mso-height-relative:page'>
<v:imagedata src="cid:image002.png@01D93C66.7AD8F570" o:title="" />
<w:wrap type="square"/>
</v:shape><![endif]--><![if !vml]><img width=148 height=178 style='width:1.5416in;height:1.8541in' src="cid:image003.png@01D93F8C.74F89600" align=left hspace=12 v:shapes="Picture_x0020_3"><![endif]><span style='font-size:12.0pt;font-family:"Arial",sans-serif'><o:p></o:p></span></p><p class=MsoNormal><span class=date-display-single><span style='font-size:12.0pt;font-family:"Arial",sans-serif'>Date: Monday, February 13, 2023</span><o:p></o:p></span></p><p class=MsoNormal><span class=date-display-single><span style='font-size:12.0pt;font-family:"Arial",sans-serif'>Time: </span></span><span class=date-display-start><span style='font-size:12.0pt;font-family:"Arial",sans-serif'>4:00PM</span></span><span class=date-display-range><span style='font-size:12.0pt;font-family:"Arial",sans-serif'> to </span></span><span class=date-display-end><span style='font-size:12.0pt;font-family:"Arial",sans-serif'>5:00PM</span></span><o:p></o:p></p><p class=MsoNormal><span class=fn><span style='font-size:12.0pt;font-family:"Arial",sans-serif'>Location: Mason Lab 211</span></span><span style='font-size:12.0pt;font-family:"Arial",sans-serif'> <span class=map-icon><span style='letter-spacing:.6pt'><a href="http://maps.google.com/?q=9+Hillhouse+Ave%2C+New+Haven%2C+CT%2C+06511%2C+us"><span style='color:windowtext'>see map</span></a> </span></span><o:p></o:p></span></p><p class=MsoNormal><span style='font-size:12.0pt;font-family:"Arial",sans-serif'>9 Hillhouse Ave<o:p></o:p></span></p><p class=MsoNormal><span class=locality><span style='font-size:12.0pt;font-family:"Arial",sans-serif'>New Haven</span></span><span style='font-size:12.0pt;font-family:"Arial",sans-serif'>, <span class=region>CT</span> <span class=postal-code>06511</span><o:p></o:p></span></p><p class=MsoNormal><span style='font-size:12.0pt;font-family:"Arial",sans-serif'><a href="http://mjt.cs.illinois.edu/"><span style='color:windowtext'>Website</span></a><o:p></o:p></span></p><p class=MsoNormal><b><span style='font-family:"Arial",sans-serif'><o:p> </o:p></span></b></p><p class=MsoNormal><b><span style='font-family:"Arial",sans-serif'><o:p> </o:p></span></b></p><p class=MsoNormal><b><span style='font-family:"Arial",sans-serif'><o:p> </o:p></span></b></p><p class=MsoNormal><b><span style='font-size:15.0pt;font-family:"Arial",sans-serif'><o:p> </o:p></span></b></p><p class=MsoNormal><b><span style='font-size:15.0pt;font-family:"Arial",sans-serif'>Title: Searching for the implicit bias of deep learning<o:p></o:p></span></b></p><p class=MsoNormal><b><span style='font-family:"Arial",sans-serif'><o:p> </o:p></span></b></p><p class=MsoNormal><b><span style='font-family:"Arial",sans-serif'>Information and Abstract: <o:p></o:p></span></b></p><p style='margin:0in;box-sizing: inherit'><span style='font-family:"Arial",sans-serif'> What makes deep learning special — why is it effective in so many settings where other models fail? This talk will present recent progress from three perspectives. The first result is approximation-theoretic: deep networks can easily represent phenomena that require exponentially-sized shallow networks, decision trees, and other classical models. Secondly, I will show that their statistical generalization ability — namely, their ability to perform well on unseen testing data — is correlated with their prediction margins, a classical notion of confidence. Finally, comprising the majority of the talk, I will discuss the interaction of the preceding two perspectives with optimization: specifically, how standard descent methods are implicitly biased towards models with good generalization. Here I will present two approaches: the strong implicit bias, which studies convergence to specific well-structured objects, and the weak implicit bias, which merely ensures certain good properties eventually hold, but has a more flexible proof technique.<o:p></o:p></span></p><p style='margin:0in;box-sizing: inherit'><span style='font-family:"Arial",sans-serif'><o:p> </o:p></span></p><p style='margin:0in'><span style='font-family:"Arial",sans-serif'>Bio: Matus Telgarsky is an assistant professor at the University of Illinois, Urbana-Champaign, specializing in deep learning theory. He was fortunate to receive a PhD at UCSD under Sanjoy Dasgupta. Other highlights include: co-founding, in 2017, the Midwest ML Symposium (MMLS) with Po-Ling Loh; receiving a 2018 NSF CAREER award; and organizing two Simons Institute programs, one on deep learning theory (summer 2019), and one on generalization (fall 2024).<o:p></o:p></span></p><p class=MsoNormal><strong><i><span style='font-family:"Calibri",sans-serif'><o:p> </o:p></span></i></strong></p><p class=MsoNormal><span style='font-size:12.0pt;font-family:"Arial",sans-serif;color:black'>For more details and upcoming events visit our website at <a href="http://statistics.yale.edu/"><span style='color:black'>http://statistics.yale.edu/</span></a></span><o:p></o:p></p><p style='margin:0in'><span style='font-family:"Arial",sans-serif'><o:p> </o:p></span></p><h2 style='margin:0in;box-sizing: inherit;font-feature-settings: "kern", "liga", "dlig"'><span style='font-family:"Arial",sans-serif;font-weight:normal'>Department of Statistics and Data Science<o:p></o:p></span></h2><p style='margin:0in;box-sizing: inherit'><span style='font-size:9.0pt;font-family:"Arial",sans-serif;color:black'>Yale University<br>24 Hillhouse Avenue<br>New Haven, CT 06511<o:p></o:p></span></p><p style='margin:0in;box-sizing: inherit'><span style='font-size:9.0pt;font-family:"Arial",sans-serif;color:black'>t 203.432.0666<br>f 203.432.0633<o:p></o:p></span></p><p class=MsoNormal style='line-height:18.0pt;background:white'><o:p> </o:p></p><p class=MsoNormal><o:p> </o:p></p></div></body></html>