<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
</head>
<body style="word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;" class="">
<i class="">Department of Computer Science Seminar</i>
<div class=""><i class=""><br class="">
</i></div>
<div class=""><span class=""><b class="">Emily Diana</b></span></div>
<div class=""><b class="">PhD Candidate, Department of Statistics and Data Science </b></div>
<div class=""><b class="">Wharton School, University of Pennsylvania </b></div>
<div class=""><b class=""><br class="">
</b></div>
<div class=""><b class="">Tuesday, January 31st</b></div>
<div class=""><b class="">2:00pm - 3:00pm </b></div>
<div class=""><b class="">In Person: John Crerar Library 390</b></div>
<div class=""><b class=""><br class="">
</b></div>
<div class=""><b class="">Title: </b><span class="" style="font-family: Calibri, sans-serif;"><b class="">Addressing Algorithmic Bias and Disclosiveness: Minimax Fairness and Multiaccurate Proxies</b></span></div>
<div class=""><span class="" style="font-family: Calibri, sans-serif;"><b class=""><br class="">
</b></span></div>
<div class=""><span class="" style="font-family: Calibri, sans-serif;"><b class="">Abstract:</b></span></div>
<div class="">While data science enables rapid societal advancement, deferring decisions to machines does not automatically avoid egregious equity or privacy violations. Without safeguards in the scientific process --- from data collection to algorithm design
to model deployment --- machine learning models can easily inherit or amplify existing biases and vulnerabilities present in society. My research focuses on explicitly encoding algorithms with ethical norms and constructing frameworks ensuring that statistics
and machine learning methods are deployed in a socially responsible manner. In particular, I develop theoretically rigorous and empirically verified algorithms to mitigate automated bias and protect individual privacy.</div>
<div class="">
<p class="MsoNormal"><o:p class=""></o:p></p>
<p class="MsoNormal">I will highlight this through two main contributions:<o:p class=""></o:p></p>
<p class="MsoNormal">(1) A new oracle-efficient and convergent algorithm to provably achieve minimax group fairness -- fairness measured by worst-case outcomes across groups -- in general settings (“Minimax Group Fairness: Algorithms and Experiments,” <a href="https://dl.acm.org/doi/10.1145/3461702.3462523" class="">https://dl.acm.org/doi/10.1145/3461702.3462523</a>).<o:p class=""></o:p></p>
<p class="MsoNormal">(2) A framework for producing a sensitive attribute proxy that allows one to train a fair model even when the original sensitive features are not available (“Multiaccurate Proxies for Downstream Fairness,” <a href="https://dl.acm.org/doi/10.1145/3531146.3533180" class="">https://dl.acm.org/doi/10.1145/3531146.3533180</a>).<o:p class=""></o:p></p>
</div>
<div class=""><b class="">Bio:</b></div>
<div class=""><span class="" style="line-height: 12.84000015258789px; font-family: Calibri, sans-serif;">Emily Diana is a Ph.D. candidate in Statistics and Data Science at the Wharton School of the University of Pennsylvania, where her research focuses on the
intersection of ethical algorithm design and socially responsible machine learning. She holds a B.A. in Applied Mathematics from Yale College and an M.S. in Statistics from Stanford University. Before graduate school, she spent two years as a software developer
at Lawrence Livermore National Laboratory (LLNL), working on high-performance computing and government finite element physics simulation codes. She is honored to be the 2022 recipient of Wharton’s J. Parker Memorial Bursk Prize for Excellence in Research and
to have been recognized as both a 2022 Future Leader in Data Science by the Michigan Institute for Data Science and a 2021 Rising Star in EECS by MIT. More information can be found on her website at <a href="http://www.emilydiana.com/" class="">www.emilydiana.com</a>.</span>
</div>
<div class=""><br class="">
<div class=""><img id="<9FCE48C4-F4EC-49B9-B32B-C5FD3506952C>" alt="EmilyDiana.jpg" class="Apple-web-attachment Apple-edge-to-edge-visual-media" apple-inline="yes" style="opacity: 1;" src="cid:9FCE48C4-F4EC-49B9-B32B-C5FD3506952C"></div>
</div>
<div class="">
<div><br class="">
</div>
<div>---</div>
<div>Holly Santos<br class="">
Executive Assistant to Michael J. Franklin, Chairman<br class="">
Department of Computer Science<br class="">
The University of Chicago<br class="">
5730 S Ellis Ave-217 Chicago, IL 60637<br class="">
P: 773-834-8977<br class="">
<a href="mailto:hsantos@uchicago.edu" class="">hsantos@uchicago.edu</a><br class="">
</div>
</div>
<br class="">
</body>
</html>