Date & Time:
February 12, 2020 10:30 am – 11:30 am
Crerar 390, 5730 S. Ellis Ave., Chicago, IL,
02/12/2020 10:30 AM 02/12/2020 11:30 AM America/Chicago Simon Du (IAS/Princeton) – Foundations of Learning Systems with (Deep) Function Approximators Crerar 390, 5730 S. Ellis Ave., Chicago, IL,

Foundations of Learning Systems with (Deep) Function Approximators

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.

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. 

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.

Host: Michael Maire

Simon Du

Postdoctoral Researcher, Institute for Advanced Study, Princeton

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.

Related News & Events

UChicago CS News

UChicago Hosts NSF Workshop on Frontiers of Quantum Advantage

Aug 15, 2022
UChicago CS News

New 2022-23 CS Faculty Add Expertise in Linguistics, Visualization, Economics, and Data Science Education

Aug 11, 2022
In the News

UChicago Co-Leads $10 Million NSF Institute on Foundations of Data Science

Aug 09, 2022
In the News

Bill Fefferman Comments on New Standards for Quantum-Proof Cryptography

Jul 07, 2022
UChicago CS News

UChicago London Colloquium Features Data Science, Quantum Research

Jul 01, 2022
UChicago CS News

Single Sign-On Migration for Chameleon Project Receives PEARC Best Paper Award

Jun 27, 2022
UChicago CS News

EPiQC Post-Doc Pens Op-Ed on Potential of Quantum Computing for Chemistry

Jun 24, 2022
UChicago CS News

Faculty Bill Fefferman and Chenhao Tan Receive Google Research Scholar Awards

Jun 21, 2022

Data Science Institute Summit

Jun 15, 2022
UChicago CS News

Prof. Yanjing Li Receives Under-40 Innovators Award from DAC

Jun 15, 2022
In the News

Nick Feamster Talks Internet Equity on Light Reading Podcast

Jun 09, 2022
UChicago CS News

Prof. Andrew A. Chien Named to DARPA ISAT Study Group

Jun 07, 2022
arrow-down-largearrow-left-largearrow-right-large-greyarrow-right-large-yellowarrow-right-largearrow-right-smallbutton-arrowclosedocumentfacebookfacet-arrow-down-whitefacet-arrow-downPage 1CheckedCheckedicon-apple-t5backgroundLayer 1icon-google-t5icon-office365-t5icon-outlook-t5backgroundLayer 1icon-outlookcom-t5backgroundLayer 1icon-yahoo-t5backgroundLayer 1internal-yellowinternalintranetlinkedinlinkoutpauseplaypresentationsearch-bluesearchshareslider-arrow-nextslider-arrow-prevtwittervideoyoutube