<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=Windows-1252">
<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:Helvetica;
panose-1:0 0 0 0 0 0 0 0 0 0;}
@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:10.0pt;
font-family:"Calibri",sans-serif;}
p.p1, li.p1, div.p1
{mso-style-name:p1;
margin:0in;
font-size:8.5pt;
font-family:Helvetica;
color:#FF9400;}
span.EmailStyle19
{mso-style-type:personal-reply;
font-family:"Calibri",sans-serif;
color:windowtext;}
.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="1026" />
</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="p1"><i><span style="font-size:12.0pt;color:windowtext"><o:p> </o:p></span></i></p>
<p class="p1"><i><span style="font-size:12.0pt;color:windowtext"><o:p> </o:p></span></i></p>
<p class="p1"><i><span style="font-size:12.0pt;color:#C00000">UNIVERSITY OF CHICAGO</span></i><o:p></o:p></p>
<p class="p1"><i><span style="font-size:12.0pt;color:#C00000">COMPUTER SCIENCE DEPARTMENT</span></i><o:p></o:p></p>
<p class="p1"><i><span style="font-size:12.0pt;color:#C00000">PRESENTS</span></i><o:p></o:p></p>
<p class="MsoNormal"><span style="font-size:11.0pt"> </span><o:p></o:p></p>
<p class="MsoNormal"><span style="font-size:11.0pt">
</span><o:p></o:p></p>
<p class="MsoNormal"><span style="font-size:11.0pt"> </span><o:p></o:p></p>
<p class="MsoNormal"><b><span style="font-size:12.0pt;font-family:Helvetica">Omer Reingold</span></b><o:p></o:p></p>
<p class="MsoNormal"><b><span style="font-size:11.0pt;font-family:Helvetica">Stanford University</span></b><o:p></o:p></p>
<p class="MsoNormal"><b><span style="font-size:11.0pt;font-family:Helvetica"> </span></b><o:p></o:p></p>
<p class="MsoNormal"> <img width="153" height="157" style="width:1.5937in;height:1.6354in" id="Picture_x0020_4" src="cid:image001.jpg@01D8531B.DD5B24F0"><o:p></o:p></p>
<p class="MsoNormal"><b><span style="font-size:11.0pt;font-family:Helvetica"> </span></b><o:p></o:p></p>
<p class="MsoNormal"><span style="font-size:11.0pt"> </span><o:p></o:p></p>
<p class="MsoNormal"><b><span style="font-size:11.0pt">Tuesday, May 3, 2022 at 3:30pm</span></b><o:p></o:p></p>
<p class="MsoNormal"><b><span style="font-size:11.0pt;background:yellow;mso-highlight:yellow">Kent Chemical Laboratory, Room 107</span></b><o:p></o:p></p>
<p class="MsoNormal"><span style="font-size:11.0pt"> </span><o:p></o:p></p>
<p class="MsoNormal" align="center" style="text-align:center;background:white"><b><span style="font-size:14.0pt;font-family:"Arial",sans-serif;color:black"> </span></b><o:p></o:p></p>
<p class="MsoNormal" style="margin-bottom:8.0pt;line-height:11.75pt"><b><span style="font-size:11.0pt;font-family:"Arial",sans-serif;color:black">“Algorithmic Fairness, Loss Minimization and Outcome Indistinguishability”</span></b><o:p></o:p></p>
<p class="MsoNormal" style="margin-bottom:8.0pt;line-height:11.75pt"><span style="font-size:11.0pt;font-family:"Arial",sans-serif;color:black"> </span><o:p></o:p></p>
<p class="MsoNormal" style="margin-bottom:8.0pt;line-height:11.75pt"><b><span style="font-size:11.0pt;font-family:"Arial",sans-serif;color:black">Abstract:</span></b><span style="font-size:11.0pt;font-family:"Arial",sans-serif;color:black">
</span><span style="font-size:11.0pt;font-family:"Arial",sans-serif;color:#3E3E3E">Training a predictor to minimize a loss function fixed in advance is the dominant paradigm in machine learning. However, loss minimization by itself might fail to satisfy properties
that come naturally in the context of algorithmic fairness. To remedy this, multi-group fairness notions such as multi calibration have been proposed, which require the predictor to share certain statistical properties of the ground truth, even when conditioned
on a rich family of subgroups. These notions could be understood from the perspective of computational indistinguishability through the notion of outcome indistinguishability where a predictor can be viewed as giving a model of events that cannot be refused from
empiric evidence within some computational bound.</span><o:p></o:p></p>
<p class="MsoNormal" style="margin-bottom:8.0pt;line-height:11.75pt"><span style="font-size:11.0pt;font-family:"Arial",sans-serif;color:black">While differently motivated, this alternative paradigm for training predictors gives unexpected consequences, including:</span><o:p></o:p></p>
<p class="MsoNormal" style="margin-bottom:8.0pt;line-height:11.75pt"><span style="font-size:11.0pt;font-family:"Arial",sans-serif;color:black">1. Practical methods for learning in a heterogeneous population, employed in the field to predict COVID-19 complications
at a very early stage of the pandemic.</span><o:p></o:p></p>
<p class="MsoNormal" style="margin-bottom:8.0pt;line-height:11.75pt"><span style="font-size:11.0pt;font-family:"Arial",sans-serif;color:black">2. A computational perspective on the meaning of individual probabilities.</span><o:p></o:p></p>
<p class="MsoNormal" style="margin-bottom:8.0pt;line-height:11.75pt"><span style="font-size:11.0pt;font-family:"Arial",sans-serif;color:black">3. A rigorous new paradigm for loss minimization in machine learning, through the notion of omni predictors, that
simultaneously applies to a wide class of loss-functions, allowing the specific loss function to be ignored at the time of learning.</span><o:p></o:p></p>
<p class="MsoNormal" style="margin-bottom:8.0pt;line-height:11.75pt"><span style="font-size:11.0pt;font-family:"Arial",sans-serif;color:black">4. A method for adapting a statistical study on one probability distribution to another, which is blind to the target
distribution at the time of inference and is competitive with wide-spread methods based on propensity scoring.</span><o:p></o:p></p>
<p class="MsoNormal" style="margin-bottom:8.0pt;line-height:11.75pt"><span style="font-size:11.0pt;font-family:"Arial",sans-serif;color:black">Based on a sequence of works joint with (subsets of) Cynthia Dwork, , Shafi Goldwasser, Parikshit Gopalan, Úrsula
Hébert-Johnson, Adam Kalai, Christoph Kern, Michael P. Kim, Frauke Kreuter, Guy N. Rothblum, Vatsal Sharan, Udi Wieder, Gal Yona</span><o:p></o:p></p>
<p class="MsoNormal" style="margin-bottom:8.0pt;line-height:11.75pt"><span style="font-size:11.0pt;font-family:"Arial",sans-serif;color:black"> </span><o:p></o:p></p>
<p class="MsoNormal" style="margin-bottom:8.0pt;line-height:11.75pt"><b><span style="font-size:11.0pt;font-family:"Arial",sans-serif;color:black">Bio:</span></b><span style="font-size:11.0pt;font-family:"Arial",sans-serif;color:black"> Omer Reingold is the
Rajeev Motwani professor of computer science at Stanford University and the director of the Simons Collaboration on the Theory of Algorithmic Fairness. Past positions include the Weizmann Institute of Science, Microsoft Research, the Institute for Advanced
Study in Princeton, NJ, AT&T Labs and Samsung Research America. His research is in the foundations of computer science and most notably in computational complexity, cryptography and the societal impact of computation. He is an ACM Fellow and a Simons Investigator.
Among his distinctions are the 2005 Grace Murray Hopper Award and the 2009 Gödel Prize. </span><o:p></o:p></p>
<div>
<div>
<p class="MsoNormal"><span style="font-size:11.0pt;color:black"> </span><o:p></o:p></p>
<p class="MsoNormal"><span style="font-size:11.0pt;color:black"> </span><o:p></o:p></p>
<p class="MsoNormal"><b><span style="font-size:12.0pt;font-family:Helvetica">Host:
</span></b><b><span style="font-size:14.0pt">Alex Razborov</span></b><o:p></o:p></p>
<p class="MsoNormal"><b><span style="font-size:12.0pt;font-family:Helvetica"> </span></b><o:p></o:p></p>
<p class="MsoNormal"><span style="font-size:11.0pt;color:black"> </span><o:p></o:p></p>
<p class="MsoNormal"><span style="font-size:11.0pt"> </span><o:p></o:p></p>
<p class="MsoNormal"><span style="font-size:11.0pt"> </span><o:p></o:p></p>
<p class="MsoNormal"><span style="font-size:11.0pt">-- </span><o:p></o:p></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Arial",sans-serif">Jose J Fragoso</span><o:p></o:p></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Arial",sans-serif">Project Assistant IV</span><o:p></o:p></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Arial",sans-serif">Computer Science Department</span><o:p></o:p></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Arial",sans-serif">5730 S. Ellis – Room 200C</span><o:p></o:p></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Arial",sans-serif">Chicago, IL. 60637</span><o:p></o:p></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Arial",sans-serif">jfragoso@uchicago.edu</span><o:p></o:p></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Arial",sans-serif">(773) 702-6614</span><o:p></o:p></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Arial",sans-serif">(773) 702-8487 FAX</span><o:p></o:p></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Arial",sans-serif"> </span><o:p></o:p></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Arial",sans-serif"><img width="92" height="92" style="width:.9583in;height:.9583in" id="Picture_x0020_1" src="cid:image003.png@01D83D68.0E6B3630" alt="signature_1572818061"></span><o:p></o:p></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Arial",sans-serif"> </span><o:p></o:p></p>
</div>
</div>
<p class="MsoNormal"><span style="font-size:11.0pt"> </span><o:p></o:p></p>
<p class="MsoNormal"><span style="font-size:11.0pt"> </span><o:p></o:p></p>
</div>
</body>
</html>