<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 dir="auto" class="" style="word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;"><div dir="auto" class="" style="word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;"><div dir="auto" class="" style="word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;"><div dir="auto" class="" style="word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;"><div dir="auto" class="" style="word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;"><div dir="auto" class="" style="word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;"><div dir="auto" class="" style="word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;"><div class="" style="word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;"><div dir="auto" class="" style="word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;"><div dir="auto" class="" style="word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;"><div dir="auto" class="" style="word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;"><div dir="auto" class="" style="word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;"><div dir="auto" class="" style="word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;"><div dir="auto" class="" style="word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;"><div class=""><span class=""><font size="4" class=""><span class="" style="orphans: 2; widows: 2;">UNIVERSITY OF CHICAGO</span><br class="" style="orphans: 2; widows: 2;"><span class="" style="orphans: 2; widows: 2;">DEPARTMENT OF COMPUTER SCIENCE</span></font></span></div><div class="" style="orphans: 2; widows: 2;"><span class=""><font size="4" class="">PRESENTS</font></span></div><div class="" style="orphans: 2; widows: 2;"><span class="" style="font-size: 15px;"><br class=""></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;"><span class="" style="font-size: 14px;"></span></div></div></div></div></div><span id="docs-internal-guid-de668218-7fff-220a-42c4-c3d01efd7aaf" class="" style="font-family: -webkit-standard;"><div class="" style="line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt;"></div></span><span class="" style="font-size: 12pt; font-family: Helvetica, sans-serif;"></span></div></div></div><div class="" style="word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;"><div dir="auto" class="" style="word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;"><div dir="auto" class="" style="word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;"></div></div></div></div></div></div></div></div></div></div><img apple-inline="yes" id="61F99B18-93C1-489C-8882-0DB073EEA92E" class="" src="cid:D78D9EF1-67AE-449F-B9D2-F029C49E032F@cs.uchicago.edu"><br class=""><div dir="auto" class="" style="word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;"><div dir="auto" class="" style="word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;"><br class=""><b class="" style="orphans: 2; widows: 2;"><font size="4" class=""><div class=""><b class=""><span class="" style="font-size: 12pt; font-family: "Times New Roman", serif;"></span></b></div><div class=""><b class=""><font size="4" class="">Simon Du</font></b></div></font></b><div dir="auto" class="" style="word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;"><div dir="auto" class="" style="word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;"><div dir="auto" class="" style="word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;"><div dir="auto" class="" style="word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;"><div dir="auto" class="" style="word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;"><div class="" style="word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;"><div dir="auto" class="" style="word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;"><div dir="auto" class="" style="word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;"><div dir="auto" class="" style="word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;"><div dir="auto" class="" style="word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;"><div dir="auto" class="" style="word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;"><div dir="auto" class="" style="word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;"><div class="" style="orphans: 2; widows: 2;"><div class="" style="margin: 0in 0in 0.0001pt;"><i class=""><font size="4" class="">Institute for Advanced Study</font></i></div><div class="" style="margin: 0in 0in 0.0001pt;"><span class="" style="font-size: 14px;"><i class=""><p class="MsoNormal" align="center"><o:p class=""></o:p></p></i></span><div class=""><br class=""></div></div><div class="" style="margin: 0in 0in 0.0001pt;"><span class=""><b class=""><font class="" size="4">Wednesday, February 12th at 10:30 am<br class="">Crerar 390</font></b><br class=""></span></div></div><div class=""><div class="" style="text-align: center;"><font size="4" class=""><font class=""><span class=""><b class="" style="color: rgb(33, 33, 33);"><br class=""></b></span></font></font></div><div class=""><font size="4" class=""><font class=""><span class=""><b class="" style="color: rgb(33, 33, 33);">Title: </b></span></font></font><font size="4" class=""><b class="">Foundations of Learning Systems with (Deep) Function Approximators </b></font></div><div class="" style="color: rgb(33, 33, 33);"><b class=""><font class="" style="font-size: 15px;"><br class=""></font></b></div><div class="" style="color: rgb(33, 33, 33);"><b class=""><font class="" size="4">Abstract:</font></b></div><div class=""><font class=""><span class=""><div class="" style="font-variant-ligatures: normal; background-color: rgb(255, 255, 255);"><div class=""><font class="" size="4"><span class=""><span id="docs-internal-guid-bf351367-7fff-5067-8c8e-0130cc54a81c" class=""><div class="" style="line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt;"><span class=""><span class=""><span class=""><span class=""><span class=""><span class="" style="white-space: pre-wrap;">Function approximators, such as deep neural networks, play a crucial role in building learning systems that make predictions and decisions. In this talk, I will discuss my work on understanding, designing, and applying function approximators.<br class=""> <br class="">First, I will focus on understanding deep neural networks. The main result is that the over-parameterized neural network is equivalent to a new kernel, Neural Tangent Kernel. This equivalence implies two surprising phenomena: 1) the simple algorithm gradient descent provably finds the global optimum of the highly non-convex empirical risk, and 2) the learned neural network generalizes well despite being highly over-parameterized. Furthermore, this equivalence helps us design a new class of function approximators: we transform (fully-connected and graph) neural networks to (fully-connected and graph) Neural Tangent Kernels, which achieve superior performance on standard benchmarks. <br class=""> <br class="">In the second part of the talk, I will focus on applying function approximators to decision-making, aka reinforcement learning, problems. In sharp contrast to the (simpler) supervised prediction problems, solving reinforcement learning problems requires an exponential number of samples, even if one applies function approximators. I will then discuss what additional structures that permit statistically efficient algorithms.</span><br class=""><br class=""></span></span></span></span></span></div></span></span><b class="" style="color: rgb(33, 33, 33);">Bio:</b></font></div></div></span></font></div><div class=""><div class="" style="font-variant-ligatures: normal; background-color: rgb(255, 255, 255);"><font color="#222222" class=""><font size="4" class=""><i class="">Simon S. Du is a postdoc at the Institute for Advanced Study of Princeton, hosted by Sanjeev Arora. He completed his Ph.D. in Machine Learning at Carnegie Mellon University, where he was co-advised by Aarti Singh and Barnabás Póczos. Previously, he studied EECS and EMS at UC Berkeley. He has also spent time at Simons Institute and research labs of Facebook, Google, and Microsoft. His research interests are broadly in machine learning, with a focus on the foundations of deep learning and reinforcement learning.</i><br class=""><i class=""> </i></font><br class=""><i class=""><b class=""><font size="4" class="">Host: Michael Maire</font></b></i></font></div></div></div></div></div></div></div></div></div></div></div></div></div></div></div></div></div></body></html>