<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=""><div class=""><span class="" style="font-size: 14px; orphans: 2; widows: 2;">UNIVERSITY OF CHICAGO</span><br class="" style="font-size: 14px; orphans: 2; widows: 2;"><span class="" style="font-size: 14px; orphans: 2; widows: 2;">DEPARTMENT OF COMPUTER SCIENCE</span></div><div class="" style="orphans: 2; widows: 2;"><span class="" style="font-size: 14px;">PRESENTS</span></div><div class="" style="orphans: 2; widows: 2;"><span class="" style="font-size: 14px;"><br class=""></span></div><div class="" style="orphans: 2; widows: 2;"><img apple-inline="yes" id="3DD72D01-2DB5-4F59-BE4F-C0E7CB4716F2" src="cid:ACC14DD0-1D0B-4375-9123-A95C38586043@cs.uchicago.edu" class=""></div><div class="" style="orphans: 2; widows: 2;"><br class=""></div><div class="" style="orphans: 2; widows: 2;"><div class="" style="margin: 0in 0in 0.0001pt;"><span class="" style="font-size: 14px;"><b class="">Si Si</b></span></div><div class="" style="margin: 0in 0in 0.0001pt;"><span class="" style="font-size: 14px;"><span class=""><i class="">Google Research</i></span></span></div><div class="" style="margin: 0in 0in 0.0001pt;"><br class=""></div><div class="" style="margin: 0in 0in 0.0001pt;"><b class=""><font class="" style="font-size: 14px;"><br class=""></font></b></div><div class="" style="margin: 0in 0in 0.0001pt;"><span class="" style="font-size: 14px;"><b class=""><font class="">Monday, April 2, 2018 at 2:30 pm <br class="">Ryerson 251</font></b><br class=""></span></div></div><div class="" style="orphans: 2; widows: 2;"><span class="" style="font-size: 14px;"><br class=""></span></div><div class=""><br class=""></div><div class=""><div class=""><b class="" style="color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14px;">Title: </b><span class="" style="color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14px;">On-device machine learning: small models and fast prediction</span></div><div class="" style="color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14px;"><b class=""><br class=""></b></div><div class="" style="color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14px;"><b class="">Abstract:</b></div><div class=""><font color="#212121" face="Roboto, Helvetica, Arial, sans-serif" class=""><span class=""><span class=""><span style="font-size: 14px;" class="">Many complex machine learning models have demonstrated tremendous success for massive data. However, these advances are not necessarily feasible when deploying these models to devices due to large model size and evaluation cost. In many real-world applications such as robotics, self-driving car, and smartphone apps, the learning tasks need to be carried out in a timely fashion on a computation and memory limited platform. Therefore, it is extremely important to study building “small” models from “big” machine learning models. The main topic of my talk is to investigate how to reduce the model size and speed up the elevation for complex machine learning models while maintaining similar accuracy. Specifically, I will discuss how to compress the model and achieve fast prediction for different real-world machine learning applications including matrix approximation and extreme classification.<br class=""><br class=""><br class=""></span></span></span></font><b class="" style="color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14px;">Bio:</b></div><div class=""><span style="color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14px;" class="">Si Si is a</span><span style="color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14px;" class=""> </span><span style="color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14px;" class="">researcher and software engineer at Google research. Her research focus is</span><span style="color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14px;" class=""> </span><span style="color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14px;" class="">developing scalable machine learning models. Si obtained her bachelor's degree</span><span style="color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14px;" class=""> </span><span style="color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14px;" class="">from the University of Science and Technology of China in 2008, M.Phil. degree</span><span style="color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14px;" class=""> </span><span style="color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14px;" class="">in 2010 from University of Hong Kong, and Ph.D. from University of Texas at</span><span style="color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14px;" class=""> </span><span style="color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14px;" class="">Austin in</span><span style="color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14px;" class=""> </span><span style="color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14px;" class="">2016. She is the recipient of the MCD fellowship in 2010-2013, and</span><span style="color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14px;" class=""> </span><span style="color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14px;" class="">the best paper award in ICDM 2012. Si was selected as one of the Rising Stars in</span><span style="color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14px;" class=""> EECS 2017.</span></div><div class=""><font color="#212121" face="Roboto, Helvetica, Arial, sans-serif" class=""><span class="" style="font-size: 14px;"><br class=""></span></font></div><div class=""><div class="" style="color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14px;"><b class="">Host: Ben Zhao</b></div><div class="" style="color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14px;"><br class=""></div><div class="" style="color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif;"><i class=""><font size="2" class="">Refreshments served after the talk in Ry. 255</font></i></div><div class="" style="color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif;"><i class=""><font size="2" class=""><br class=""></font></i></div><div class="" style="color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif;"><font size="2" class=""><i class=""><font class="">Link to PDF: </font></i><a href="https://www.cs.uchicago.edu/sites/cs/files/uploads/seminar_announcements/Si poster.pdf" class="">https://www.cs.uchicago.edu/sites/cs/files/uploads/seminar_announcements/Si%20poster.pdf</a></font></div></div></div></body></html>