<div dir="ltr"><div><div class="gmail_default" style=""><font face="georgia, serif" style="" color="#000000"><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">    Wednesday, November 12th at <b style=""><font style="background-color:rgb(255,255,0)">**</font></b><b style="background-color:rgb(255,255,0)">10:30am CT**</b><b style=""> </b></font></font></font></div><div class="gmail_default"><font face="georgia, serif" color="#000000"><font style="vertical-align:inherit"><font style="vertical-align:inherit"><b><br></b></font></font></font></div><div class="gmail_default"><font face="georgia, serif" color="#000000"></font></div><div class="gmail_default"><font face="georgia, serif" color="#000000"><b>Where:       </b>Talk will be given <font style="font-weight:bold"><u>live, in-person</u></font><font style="font-weight:bold"> </font>at</font></div><p class="MsoNormal" style="margin:0in;line-height:normal;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><font face="georgia, serif" color="#000000">                       TTIC, 6045 S. Kenwood Avenue</font></p><p class="MsoNormal" style="margin:0in;line-height:normal;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><font color="#000000" face="georgia, serif">                       5th Floor, Room 530<b> </b></font></p><p class="MsoNormal" style="margin:0in;line-height:normal;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><b><font face="georgia, serif" color="#000000"><br></font></b></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="georgia, serif" color="#000000"><b style="letter-spacing:0.2px">Virtually:</b><span style="letter-spacing:0.2px">  via Panopto </span>(<a href="https://uchicago.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=4ff56911-9597-4a72-95f4-b37701267e2d" target="_blank">livestream</a><span style="letter-spacing:0.2px">)</span><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="georgia, serif" color="#000000"><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="georgia, serif" color="#000000"><font style="vertical-align:inherit"><font style="vertical-align:inherit"><b>Who: </b>         </font></font>Konstantinos Stavropoulos<span class="gmail_default" style="">, </span></font><font face="georgia, serif" color="#000000">University of Texas at Austin</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"></p><div><p style="letter-spacing:0.2px"><font face="georgia, serif" color="#000000"><span style="letter-spacing:normal"><b>Title:</b>          </span><span style="letter-spacing:normal">Efficient Learning Algorithms under (Heavy) Contamination</span></font></p><div><font face="georgia, serif" color="#000000"><b>Abstract:  </b>In this talk, I will present a series of new results in supervised learning from contaminated datasets, based on a general outlier removal algorithm inspired by recent work on learning with distribution shift. Specifically:</font></div><font face="georgia, serif" color="#000000"><br>We will show that any function class that can be approximated by low-degree polynomials with respect to a hypercontractive distribution can be efficiently learned under bounded contamination (also known as nasty noise). This resolves a longstanding gap between the complexity of agnostic learning and learning with contamination, even though it was widely believed that low-degree approximators only implied tolerance to label noise.<br>For any function class that admits the (stronger) notion of sandwiching approximators, we obtain near-optimal learning guarantees even with respect to heavy additive contamination, where far more than 1/2 of the training set may be added adversarially. Prior related work held only for regression and in a list-decodable setting.<br>These results significantly advance our understanding of efficient supervised learning under contamination, a setting that has been much less studied than its unsupervised counterpart. As a notable application, our framework yields the first quasipolynomial-time algorithm for learning constant-depth circuits (AC⁰) under bounded contamination, extending the seminal result of Linial, Mansour, and Nisan on learning AC⁰ under adversarial label noise.</font></div><div><div><font face="georgia, serif" color="#000000"><br></font></div><div><font face="georgia, serif" color="#000000"><b>Bio</b>: Kostas Stavropoulos is a fifth-year Ph.D. student in Computer Science at the University of Texas at Austin, advised by Prof. Adam Klivans. He is a 2025 Apple Scholar in AI/ML. His research focuses on the theory of machine learning, particularly on designing efficient algorithms with provable guarantees under minimal—or at least verifiable—assumptions, especially in challenging settings such as learning under distribution shift and data contamination.</font></div><div><font face="georgia, serif" color="#000000"><br></font></div></div><div><font face="georgia, serif" color="#000000"><b>Host:<span class="gmail_default"> <a href="mailto:nati@ttic.edu" target="_blank">Nati Srebro</a></span></b></font></div><br clear="all"></div><div><div dir="ltr" class="gmail_signature" data-smartmail="gmail_signature"><div dir="ltr"><b style="background-color:rgb(255,255,255)"><font color="#3d85c6">Brandie Jones </font></b><div><div><div><font color="#3d85c6"><b><i>Executive </i></b></font><b style="color:rgb(61,133,198)"><i>Administrative Assistant</i></b></div></div><div><b style="color:rgb(61,133,198)"><i>Outreach Administrator </i></b></div><div><span style="background-color:rgb(255,255,255)"><font color="#3d85c6">Toyota Technological Institute</font></span></div><div><span style="background-color:rgb(255,255,255)"><font color="#3d85c6">6045 S. Kenwood Avenue</font></span></div><div><span style="background-color:rgb(255,255,255)"><font color="#3d85c6">Chicago, IL  60637</font></span></div></div><div><span style="background-color:rgb(255,255,255)"><font color="#3d85c6"><a href="http://www.ttic.edu" target="_blank">www.ttic.edu</a> </font></span></div><div><span style="background-color:rgb(255,255,255)"><font color="#3d85c6"><br></font></span></div></div></div></div></div>