<div dir="ltr"><div dir="ltr"><div class="gmail_default" style="font-size:small"><div><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, December 9th at 11:00 am</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 style="vertical-align:inherit"><font style="vertical-align:inherit">TTIC, 6045 S. Kenwood Avenue, 5th Floor, Room 526</font></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>Adam Kalai, Microsoft Research</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">    </font></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 style="vertical-align:inherit"><font style="vertical-align:inherit">  </font></font></font></p></div><div><div><font face="arial, sans-serif"><b>Title:        </b></font>Expect the Unexpected: Learning to Generalize across Similarly Different Datasets</div><p class="MsoNormal"><u></u></p><p class="MsoNormal"><u></u> </p><div><br></div><div><font face="arial, sans-serif"><b>Abstract: </b></font>People learn to drive in one city and are easily able to drive in others, exhibiting a robustness that Machine Learning algorithms often lack. We consider a model of learning where test data may be very different from training data, e.g., training data is collected in two cities but test data is from a third city (or training data is from a single city but can be appropriately subsampled). We analyze and experiment with algorithms for learning from the differences across training data splits to predict well on the unseen distribution. Our model differs from most work on domain adaptation in that: the test distribution may not even overlap with the training distribution, we have no unlabeled samples from the test distribution, and yet the training and test distributions are assumed to be drawn from the same meta-distribution over distributions. For these reasons, importance-weighting approaches are not applicable and different algorithms are necessary.</div><p class="MsoNormal"><u></u></p><p class="MsoNormal"><u></u> <u></u></p><p class="MsoNormal">Joint work with Vikas Garg (MIT), Katrina Ligett (Hebrew University), and Steven Wu (University of Minnesota).<u></u><u></u></p><p class="MsoNormal"><u></u> </p></div><div><font face="arial, sans-serif"><b><br></b></font></div><div><div><b style="font-family:arial,sans-serif">Host:</b><span style="font-family:arial,sans-serif"> <a href="mailto:avrim@ttic.edu" target="_blank">Avrim Blum</a></span><a href="mailto:madhurt@ttic.edu" target="_blank"><br></a></div><div><br></div><div><br></div><div><span style="font-size:12.8px;font-family:arial,helvetica,sans-serif">For more information on the </span><span style="font-size:12.8px;font-family:arial,helvetica,sans-serif">colloquium</span><span style="font-size:12.8px;font-family:arial,helvetica,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-size:12.8px;font-family:arial,helvetica,sans-serif">http://www.ttic.edu/colloquium.php</a>  <br></div><div><br></div></div><div><br></div><div><br></div><div><br></div><div><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"><font face="arial, helvetica, sans-serif">Mary C. Marre</font><div><font face="arial, helvetica, sans-serif">Administrative Assistant</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><br></div><br><div class="gmail_quote"><div dir="ltr" class="gmail_attr">On Sun, Dec 8, 2019 at 8:05 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 dir="ltr"><div style="font-size:small"><div><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, December 9th at 11:00 am</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 style="vertical-align:inherit"><font style="vertical-align:inherit">TTIC, 6045 S. Kenwood Avenue, 5th Floor, Room 526</font></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><span>Adam</span> <span>Kalai</span>, Microsoft Research</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">    </font></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 style="vertical-align:inherit"><font style="vertical-align:inherit">  </font></font></font></p></div><div><div><font face="arial, sans-serif"><b>Title:        </b></font>Expect the Unexpected: Learning to Generalize across Similarly Different Datasets</div><p class="MsoNormal"><u></u></p><p class="MsoNormal"><u></u> </p><div><br></div><div><font face="arial, sans-serif"><b>Abstract: </b></font>People learn to drive in one city and are easily able to drive in others, exhibiting a robustness that Machine Learning algorithms often lack. We consider a model of learning where test data may be very different from training data, e.g., training data is collected in two cities but test data is from a third city (or training data is from a single city but can be appropriately subsampled). We analyze and experiment with algorithms for learning from the differences across training data splits to predict well on the unseen distribution. Our model differs from most work on domain adaptation in that: the test distribution may not even overlap with the training distribution, we have no unlabeled samples from the test distribution, and yet the training and test distributions are assumed to be drawn from the same meta-distribution over distributions. For these reasons, importance-weighting approaches are not applicable and different algorithms are necessary.</div><p class="MsoNormal"><u></u></p><p class="MsoNormal"><u></u> <u></u></p><p class="MsoNormal">Joint work with Vikas Garg (MIT), Katrina Ligett (Hebrew University), and Steven Wu (University of Minnesota).<u></u><u></u></p><p class="MsoNormal"><u></u> </p></div><div><font face="arial, sans-serif"><b><br></b></font></div><div><div><b style="font-family:arial,sans-serif">Host:</b><span style="font-family:arial,sans-serif"> <a href="mailto:avrim@ttic.edu" target="_blank">Avrim Blum</a></span><a href="mailto:madhurt@ttic.edu" target="_blank"><br></a></div><div><br></div><div><br></div><div><span style="font-size:12.8px;font-family:arial,helvetica,sans-serif">For more information on the </span><span style="font-size:12.8px;font-family:arial,helvetica,sans-serif">colloquium</span><span style="font-size:12.8px;font-family:arial,helvetica,sans-serif"> series or to subscribe to the mailing list, please see </span><a href="http://www.ttic.edu/colloquium.php" style="font-size:12.8px;font-family:arial,helvetica,sans-serif" target="_blank">http://www.ttic.edu/colloquium.php</a>  <br></div><div><br></div></div><div><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"><font face="arial, helvetica, sans-serif">Mary C. Marre</font><div><font face="arial, helvetica, sans-serif">Administrative Assistant</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><br></div><br><div class="gmail_quote"><div dir="ltr" class="gmail_attr">On Mon, Dec 2, 2019 at 1:36 PM Mary Marre <<a href="mailto:mmarre@ttic.edu" target="_blank">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 style="font-size:small"><div><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, December 9th at 11:00 am</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 style="vertical-align:inherit"><font style="vertical-align:inherit">TTIC, 6045 S. Kenwood Avenue, 5th Floor, Room 526</font></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>Adam Kalai, Microsoft Research</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">    </font></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 style="vertical-align:inherit"><font style="vertical-align:inherit">  </font></font></font></p></div><div><div><font face="arial, sans-serif"><b>Title:        </b></font>Expect the Unexpected: Learning to Generalize across Similarly Different Datasets</div><p class="MsoNormal"><u></u></p><p class="MsoNormal"><u></u> </p><div><br></div><div><font face="arial, sans-serif"><b>Abstract: </b></font>People learn to drive in one city and are easily able to drive in others, exhibiting a robustness that Machine Learning algorithms often lack. We consider a model of learning where test data may be very different from training data, e.g., training data is collected in two cities but test data is from a third city (or training data is from a single city but can be appropriately subsampled). We analyze and experiment with algorithms for learning from the differences across training data splits to predict well on the unseen distribution. Our model differs from most work on domain adaptation in that: the test distribution may not even overlap with the training distribution, we have no unlabeled samples from the test distribution, and yet the training and test distributions are assumed to be drawn from the same meta-distribution over distributions. For these reasons, importance-weighting approaches are not applicable and different algorithms are necessary.</div><p class="MsoNormal"><u></u></p><p class="MsoNormal"><u></u> <u></u></p><p class="MsoNormal">Joint work with Vikas Garg (MIT), Katrina Ligett (Hebrew University), and Steven Wu (University of Minnesota).<u></u><u></u></p><p class="MsoNormal"><u></u> </p></div><div><font face="arial, sans-serif"><b><br></b></font></div><div><div><b style="font-family:arial,sans-serif">Host:</b><span style="font-family:arial,sans-serif"> <a href="mailto:avrim@ttic.edu" target="_blank">Avrim Blum</a></span><a href="mailto:madhurt@ttic.edu" target="_blank"><br></a></div><div><br></div><div><br></div><div><span style="font-size:12.8px;font-family:arial,helvetica,sans-serif">For more information on the </span><span style="font-size:12.8px;font-family:arial,helvetica,sans-serif">colloquium</span><span style="font-size:12.8px;font-family:arial,helvetica,sans-serif"> series or to subscribe to the mailing list, please see </span><a href="http://www.ttic.edu/colloquium.php" style="font-size:12.8px;font-family:arial,helvetica,sans-serif" target="_blank">http://www.ttic.edu/colloquium.php</a>  <br></div><div><br></div></div><div><br></div><div><br></div><div><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"><font face="arial, helvetica, sans-serif">Mary C. Marre</font><div><font face="arial, helvetica, sans-serif">Administrative Assistant</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>
</blockquote></div></div>
</blockquote></div></div>