<div dir="ltr"><div dir="ltr"><div class="gmail_default" style="font-size:small"><div class="gmail_default"><div class="gmail_default"><p style="font-variant-numeric:normal;font-variant-east-asian:normal;font-stretch:normal;line-height:normal;margin:0px"><font face="arial, sans-serif"><font style="vertical-align:inherit"><font style="vertical-align:inherit"><b>When:</b>    </font></font><font style="vertical-align:inherit"><font style="vertical-align:inherit">  Monday, January 25th at 11:10 am CT</font></font><br></font></p><p class="MsoNormal" style="margin:0in 0in 0.0001pt;line-height:normal;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><font face="arial, sans-serif"> </font></p><p class="MsoNormal" style="margin:0in 0in 0.0001pt;line-height:normal;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><font face="arial, sans-serif"><font style="vertical-align:inherit"><font style="vertical-align:inherit"><b>Where:</b>     </font></font><font color="#000000">Zoom Virtual Talk (</font><b><font color="#0000ff"><a href="https://uchicagogroup.zoom.us/webinar/register/WN_4ihYHm5YQbi6dXgdeOD8BQ" target="_blank">register in advance here</a></font></b><font color="#000000">)</font></font></p><p class="MsoNormal" style="margin:0in 0in 0.0001pt;line-height:normal;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><font face="arial, sans-serif"> </font></p><p class="MsoNormal" style="margin:0in 0in 0.0001pt;line-height:normal;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><font face="arial, sans-serif"><font style="vertical-align:inherit"><font style="vertical-align:inherit"><b>Who: </b>       </font></font></font>Percy Liang, Stanford University</p><p class="MsoNormal" style="margin:0in 0in 0.0001pt;line-height:normal;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><span style="color:rgba(0,0,0,0.9)"><b><font face="arial, sans-serif"><br></font></b></span></p><p class="MsoNormal" style="margin:0in 0in 0.0001pt;line-height:normal;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><span style="color:rgba(0,0,0,0.9)"><b><font face="arial, sans-serif"><br></font></b></span></p><p class="MsoNormal" style="margin:0in 0in 0.0001pt;line-height:normal;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><font face="arial, sans-serif"><span style="color:rgb(60,64,67);letter-spacing:0.2px;white-space:pre-wrap"><b>Talk:</b>        Surprises in the Quest for Robust Machine Learning</span><span style="letter-spacing:0.2px"><br style="color:rgb(60,64,67);letter-spacing:0.2px;white-space:pre-wrap"><br style="color:rgb(60,64,67);letter-spacing:0.2px;white-space:pre-wrap"></span><span style="color:rgb(60,64,67);letter-spacing:0.2px;white-space:pre-wrap"><b>Abstract: </b>Standard machine learning produces models that are accurate on average but degrade dramatically on when the test distribution of interest deviates from the training distribution.  We consider three settings where this happens: when test inputs are subject to adversarial attacks, when we are concerned with performance on minority subpopulations, and when the world simply changes (classic domain shift).  Our aim is to produce methods that are provably robust to such deviations.  In this talk, I will provide an overview of the work my group has done on this topic over the last three years.  We have found many surprises in our quest for robustness: for example, that the "more data" and "bigger models" strategy that works so well for average accuracy sometimes fails out-of-domain.  On the other hand, we have found that certain tools such as analysis of linear regression and use of unlabeled data (e.g., robust self-training) have reliably delivered promising results across a number of different settings.</span><span style="letter-spacing:0.2px"><br style="color:rgb(60,64,67);letter-spacing:0.2px;white-space:pre-wrap"><br style="color:rgb(60,64,67);letter-spacing:0.2px;white-space:pre-wrap"></span><span style="color:rgb(60,64,67);letter-spacing:0.2px;white-space:pre-wrap"><b>Bio: </b></span><span style="letter-spacing:0.2px"><br style="color:rgb(60,64,67);letter-spacing:0.2px;white-space:pre-wrap"></span><span style="color:rgb(60,64,67);letter-spacing:0.2px;white-space:pre-wrap">Percy Liang is an Associate Professor of Computer Science at Stanford University (B.S. from MIT, 2004; Ph.D. from UC Berkeley, 2011).  His research spans machine learning and natural language processing, with the goal of developing trustworthy agents that can communicate effectively with people and improve over time through interaction.  Specific topics include question answering, dialogue, program induction, interactive learning, and reliable machine learning.  His awards include the IJCAI Computers and Thought Award (2016), an NSF CAREER Award (2016), a Sloan Research Fellowship (2015), and a Microsoft Research Faculty Fellowship (2014).</span>  </font><span style="color:rgba(0,0,0,0.9)"><b><font face="arial, sans-serif"><br></font></b></span></p><p class="MsoNormal" style="margin:0in 0in 0.0001pt;line-height:normal;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><br></p><div dir="auto"><div style="margin:0px;padding:0px 0px 20px;width:1120px"><div><div id="gmail-m_4224429344967997754gmail-m_8499444526547931902gmail-m_-1916303418504908038m_171242323807179252gmail-m_-8743081643725194343gmail-:369" style="direction:ltr;margin:8px 0px 0px;padding:0px"><div id="gmail-m_4224429344967997754gmail-m_8499444526547931902gmail-m_-1916303418504908038m_171242323807179252gmail-m_-8743081643725194343gmail-:1ro" style="overflow:hidden;font-variant-numeric:normal;font-variant-east-asian:normal;font-stretch:normal;line-height:1.5"><div dir="auto"><div><div dir="auto"><b style="font-family:arial,sans-serif">Host:  </b><span style="font-family:arial,sans-serif"><a href="mailto:mcallester@ttic.edu" target="_blank"><b>David McAllester</b></a></span></div></div></div></div></div></div></div></div></div><span style="font-family:arial,sans-serif">For more information on the </span><span style="font-family:arial,sans-serif">colloquium</span><span style="font-family:arial,sans-serif"> series or to subscribe to the mailing list, please see </span><a href="http://www.ttic.edu/colloquium.php" target="_blank" style="font-family:arial,sans-serif">http://www.ttic.edu/colloquium.php</a><span style="font-family:arial,sans-serif">   </span> </div><div class="gmail_default"><br></div><div class="gmail_default"><br></div><div class="gmail_default"><br></div></div><div><div dir="ltr" class="gmail_signature" data-smartmail="gmail_signature"><div dir="ltr"><div><div dir="ltr"><div><div dir="ltr"><div><div dir="ltr"><div><div dir="ltr"><div><div dir="ltr"><div><div dir="ltr"><font face="arial, helvetica, sans-serif">Mary C. Marre</font><div><font face="arial, helvetica, sans-serif">Faculty Administrative Support</font></div><div><i><font face="arial, helvetica, sans-serif" color="#3d85c6"><b>Toyota Technological Institute</b></font></i></div><div><i><font face="arial, helvetica, sans-serif" color="#3d85c6">6045 S. Kenwood Avenue</font></i></div><div><i><font face="arial, helvetica, sans-serif" color="#3d85c6">Room 517</font></i></div><div><i><font face="arial, helvetica, sans-serif" color="#3d85c6">Chicago, IL  60637</font></i></div><div><i><font face="arial, helvetica, sans-serif">p:(773) 834-1757</font></i></div><div><i><font face="arial, helvetica, sans-serif">f: (773) 357-6970</font></i></div><div><b><i><a href="mailto:mmarre@ttic.edu" target="_blank"><font face="arial, helvetica, sans-serif">mmarre@ttic.edu</font></a></i></b></div></div></div></div></div></div></div></div></div></div></div></div></div></div></div></div><br></div><br><div class="gmail_quote"><div dir="ltr" class="gmail_attr">On Mon, Jan 18, 2021 at 4:41 PM Mary Marre <<a href="mailto:mmarre@ttic.edu">mmarre@ttic.edu</a>> wrote:<br></div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><div dir="ltr"><div><div><div><p style="font-size:small;font-variant-numeric:normal;font-variant-east-asian:normal;font-stretch:normal;line-height:normal;margin:0px"><font face="arial, sans-serif"><font style="vertical-align:inherit"><font style="vertical-align:inherit"><b>When:</b>    </font></font><font style="vertical-align:inherit"><font style="vertical-align:inherit">  Monday, January 25th at 11:10 am CT</font></font><br></font></p><p class="MsoNormal" style="font-size:small;margin:0in 0in 0.0001pt;line-height:normal;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><font face="arial, sans-serif"> </font></p><p class="MsoNormal" style="font-size:small;margin:0in 0in 0.0001pt;line-height:normal;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><font face="arial, sans-serif"><font style="vertical-align:inherit"><font style="vertical-align:inherit"><b>Where:</b>     </font></font><font color="#000000">Zoom Virtual Talk (</font><b><font color="#0000ff"><a href="https://uchicagogroup.zoom.us/webinar/register/WN_4ihYHm5YQbi6dXgdeOD8BQ" target="_blank">register in advance here</a></font></b><font color="#000000">)</font></font></p><p class="MsoNormal" style="font-size:small;margin:0in 0in 0.0001pt;line-height:normal;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><font face="arial, sans-serif"> </font></p><p class="MsoNormal" style="font-size:small;margin:0in 0in 0.0001pt;line-height:normal;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><font face="arial, sans-serif"><font style="vertical-align:inherit"><font style="vertical-align:inherit"><b>Who: </b>       </font></font></font>Percy Liang, Stanford University</p><p class="MsoNormal" style="font-size:small;margin:0in 0in 0.0001pt;line-height:normal;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><span style="color:rgba(0,0,0,0.9)"><b><font face="arial, sans-serif"><br></font></b></span></p><p class="MsoNormal" style="font-size:small;margin:0in 0in 0.0001pt;line-height:normal;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><span style="color:rgba(0,0,0,0.9)"><b><font face="arial, sans-serif"><br></font></b></span></p><p class="MsoNormal" style="margin:0in 0in 0.0001pt;line-height:normal;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><font face="arial, sans-serif"><span style="color:rgb(60,64,67);letter-spacing:0.2px;white-space:pre-wrap"><b>Talk:</b>        Surprises in the Quest for Robust Machine Learning</span><span style="letter-spacing:0.2px"><br style="color:rgb(60,64,67);letter-spacing:0.2px;white-space:pre-wrap"><br style="color:rgb(60,64,67);letter-spacing:0.2px;white-space:pre-wrap"></span><span style="color:rgb(60,64,67);letter-spacing:0.2px;white-space:pre-wrap"><b>Abstract: </b>Standard machine learning produces models that are accurate on average but degrade dramatically on when the test distribution of interest deviates from the training distribution.  We consider three settings where this happens: when test inputs are subject to adversarial attacks, when we are concerned with performance on minority subpopulations, and when the world simply changes (classic domain shift).  Our aim is to produce methods that are provably robust to such deviations.  In this talk, I will provide an overview of the work my group has done on this topic over the last three years.  We have found many surprises in our quest for robustness: for example, that the "more data" and "bigger models" strategy that works so well for average accuracy sometimes fails out-of-domain.  On the other hand, we have found that certain tools such as analysis of linear regression and use of unlabeled data (e.g., robust self-training) have reliably delivered promising results across a number of different settings.</span><span style="letter-spacing:0.2px"><br style="color:rgb(60,64,67);letter-spacing:0.2px;white-space:pre-wrap"><br style="color:rgb(60,64,67);letter-spacing:0.2px;white-space:pre-wrap"></span><span style="color:rgb(60,64,67);letter-spacing:0.2px;white-space:pre-wrap"><b>Bio: </b></span><span style="letter-spacing:0.2px"><br style="color:rgb(60,64,67);letter-spacing:0.2px;white-space:pre-wrap"></span><span style="color:rgb(60,64,67);letter-spacing:0.2px;white-space:pre-wrap">Percy Liang is an Associate Professor of Computer Science at Stanford University (B.S. from MIT, 2004; Ph.D. from UC Berkeley, 2011).  His research spans machine learning and natural language processing, with the goal of developing trustworthy agents that can communicate effectively with people and improve over time through interaction.  Specific topics include question answering, dialogue, program induction, interactive learning, and reliable machine learning.  His awards include the IJCAI Computers and Thought Award (2016), an NSF CAREER Award (2016), a Sloan Research Fellowship (2015), and a Microsoft Research Faculty Fellowship (2014).</span>  </font><span style="font-size:small;color:rgba(0,0,0,0.9)"><b><font face="arial, sans-serif"><br></font></b></span></p><p class="MsoNormal" style="font-size:small;margin:0in 0in 0.0001pt;line-height:normal;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><br></p><div dir="auto" style="font-size:small"><div style="margin:0px;padding:0px 0px 20px;width:1120px"><div><div id="gmail-m_4224429344967997754gmail-m_8499444526547931902gmail-m_-1916303418504908038m_171242323807179252gmail-m_-8743081643725194343gmail-:369" style="direction:ltr;margin:8px 0px 0px;padding:0px"><div id="gmail-m_4224429344967997754gmail-m_8499444526547931902gmail-m_-1916303418504908038m_171242323807179252gmail-m_-8743081643725194343gmail-:1ro" style="overflow:hidden;font-variant-numeric:normal;font-variant-east-asian:normal;font-stretch:normal;line-height:1.5"><div dir="auto"><div><div dir="auto"><b style="font-family:arial,sans-serif">Host:  </b><span style="font-family:arial,sans-serif"><a href="mailto:mcallester@ttic.edu" target="_blank"><b>David McAllester</b></a></span></div></div></div></div></div></div></div></div></div><span style="font-size:small;font-family:arial,sans-serif">For more information on the </span><span style="font-size:small;font-family:arial,sans-serif"><span>colloquium</span></span><span style="font-size:small;font-family:arial,sans-serif"> series or to subscribe to the mailing list, please see </span><a href="http://www.ttic.edu/colloquium.php" style="font-size:small;font-family:arial,sans-serif" target="_blank">http://www.ttic.edu/<span>colloquium</span>.php</a><span style="font-size:small;font-family:arial,sans-serif">   </span> </div><div style="font-size:small"><br></div><div style="font-size:small"><br></div><div style="font-size:small"><br></div></div><div><div dir="ltr"><div dir="ltr"><div><div dir="ltr"><div><div dir="ltr"><div><div dir="ltr"><div><div dir="ltr"><div><div dir="ltr"><div><div dir="ltr"><font face="arial, helvetica, sans-serif">Mary C. Marre</font><div><font face="arial, helvetica, sans-serif">Faculty Administrative Support</font></div><div><i><font face="arial, helvetica, sans-serif" color="#3d85c6"><b>Toyota Technological Institute</b></font></i></div><div><i><font face="arial, helvetica, sans-serif" color="#3d85c6">6045 S. Kenwood Avenue</font></i></div><div><i><font face="arial, helvetica, sans-serif" color="#3d85c6">Room 517</font></i></div><div><i><font face="arial, helvetica, sans-serif" color="#3d85c6">Chicago, IL  60637</font></i></div><div><i><font face="arial, helvetica, sans-serif">p:(773) 834-1757</font></i></div><div><i><font face="arial, helvetica, sans-serif">f: (773) 357-6970</font></i></div><div><b><i><a href="mailto:mmarre@ttic.edu" target="_blank"><font face="arial, helvetica, sans-serif">mmarre@ttic.edu</font></a></i></b></div></div></div></div></div></div></div></div></div></div></div></div></div></div></div></div></div>
</blockquote></div></div>