<html><head><meta http-equiv="Content-Type" content="text/html; charset=us-ascii"></head><body style="word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;" class=""><div dir="auto" class="" style="caret-color: rgb(0, 0, 0); color: rgb(0, 0, 0); word-wrap: break-word; line-break: after-white-space;"><font face="Arial" class=""><b class="" style="font-size: 14px;"><font color="#000000" class="">University of Chicago and Toyota Technological Institute at Chicago<br class="">Machine Learning Seminar Series</font></b><br class=""><br class=""><br class=""><b class="" style="font-size: 14px;">Dan McDonald</b><br class=""><span class="" style="font-size: 14px;">UChicago Statistics</span><br class=""><br class=""><b class="" style="font-size: 14px;">Wednesday, May 29, 2019 at 1:00 - 2:00 pm<br class=""></b><font color="#000000" class=""><span class="" style="font-size: 14px;"><b class="">Saieh Hall of Economics (SHFE) Room 203</b></span></font><br class=""><br class=""><br class=""><b class="" style="font-size: 14px;">Title:</b></font></div><div dir="auto" class="" style="caret-color: rgb(0, 0, 0); color: rgb(0, 0, 0); word-wrap: break-word; line-break: after-white-space;"><font class="" color="#000000" face="Arial" style="font-size: 15.333333015441895px;">Trend Filtering in exponential families</font><font face="Arial" class=""> <br class=""><b class="" style="font-size: 14px;"><font face="Arial" class="" style="font-weight: normal;"><b class=""><br class=""></b></font></b></font></div><div dir="auto" class="" style="caret-color: rgb(0, 0, 0); color: rgb(0, 0, 0); word-wrap: break-word; line-break: after-white-space;"><font face="Arial" class=""><span class=""><font face="Arial" class="" style="font-size: 14px;"><b class="">Abstract:</b><br class=""></font><div class=""><font color="#000000" class=""><span class="" style="font-size: 14px;">Trend filtering is a modern approach to nonparametric regression thatis more adaptive to local smoothness than splines or basisprocedures. Current analysis of trend filtering focuses on estimatinga function corrupted by Gaussian noise, but our work extends thistechnique to general exponential family distributions. This extensionis motivated by the need to study massive, gridded climate dataderived from polar-orbiting satellites. We present algorithms tailoredto large problems, theoretical results for general loss functions, andprincipled methods for tuning parameter selection without excesscomputation</span></font></div><font face="Arial" class="" style="font-size: 14px;"><br class=""><b class="">Bio:</b><br class=""></font><span class=""><font color="#000000" class=""><span class="" style="font-size: 14px;">Daniel McDonald, Visiting Assistant Professor of Statistics, studies applications of statistical machine learning. Most of his work involves providing theoretical justification for existing methodology. He is also interested in computational approximations; time series; and applications in economics, climate science, and chemistry. McDonald is visiting from Indiana University, Bloomington where he is Associate Professor of Statistics and Adjunct Associate Professor of Computer Science.</span></font><br class=""></span><div class=""><span class="" style="font-size: 14px;"><span class=""><b class=""><br class=""></b></span></span></div><div class=""><span class="" style="font-size: 14px;"><span class=""><b class="">Host: Rebecca Willett</b></span></span></div><div class=""><span class="" style="font-size: 14px;"><span class=""><b class=""><br class=""></b></span></span></div></span></font></div><div class=""></div></body></html>