Seminars

Upcoming Seminars

Fri
Oct 23
11:00 AM - 12:00 PM
Online
Assistant Professor, Georgia Institute of Technology

The focus of our work is to obtain finite-sample and/or finite-time convergence bounds of various model-free Reinforcement Learning (RL) algorithms. Many RL algorithms are special cases of Stochastic Approximation (SA), which is a popular approach for solving fixed point equations when the information is corrupted by noise. We first obtain finite-sample bounds for general SA using a generalized Moreau envelope as a smooth potential/ Lyapunov function.

Fri
Oct 30
9:00 AM - 10:00 AM
Online
Deniz Gündüz
Associate Professor, Imperial College London

Seminar will be delivered live via Zoom on Friday, October 30, 2020 at 9:00AM - 10:00AM U.S. Central Time (CDT / UTC -5).

The Zoom conferencing system is accessible to UT faculty, staff, and students with support from ITS. Otherwise, you can sign up for a free account on the Zoom website.

Thu
Nov 05
11:00 AM - 12:00 PM
Online
Cong Shen
Professor, University of Science and Technology of China

Seminar will be delivered live via Zoom on Thursday, November 5, 2020 at 11:00AM - 12:00PM U.S. Central Time (CST / UTC -6).

The Zoom conferencing system is accessible to UT faculty, staff, and students with support from ITS. Otherwise, you can sign up for a free account on the Zoom website.

Fri
Nov 13
11:00 AM - 12:00 PM
Online
Maryam Fazel
Associate Professor, University of Washington

Maryam Fazel (University of Washington)

Date: Friday, November 13, 2020
Time: 11:00 AM – 12:00 PM (CST; UTC -6)
Location: Online (Zoom link will be provided)

Title: TBD

Abstract: TBD

Recent Seminars

16 Oct 2020

Overparameterized neural networks have proved to be remarkably successful in many complex tasks such as image classification and deep reinforcement learning. In this talk, we will consider the role of explicit regularization in training overparameterized neural networks. Specifically, we consider ReLU networks and show that the landscape of commonly used regularized loss functions have the property that every local minimum has good memorization and regularization performance. Joint work with Shiyu Liang and Ruoyu Sun.

13 Oct 2020

Abstract TBA

 

Event time is 11:00AM - 12:00PM Central (CDT; UTC -5)     

Access: Seminar will be delivered live; on the date and time shown above via Zoom. Access link TBA.

The Zoom conferencing system is accessible to UT faculty, staff, and students with support from ITS. Otherwise, you can sign up for a free account on the Zoom website.