PhD Defense by Namjoon Suh

*********************************
There is now a CONTENT FREEZE for Mercury while we switch to a new platform. It began on Friday, March 10 at 6pm and will end on Wednesday, March 15 at noon. No new content can be created during this time, but all material in the system as of the beginning of the freeze will be migrated to the new platform, including users and groups. Functionally the new site is identical to the old one. webteam@gatech.edu
*********************************

Event Details
  • Date/Time:
    • Friday November 18, 2022
      9:00 am - 11:00 am
  • Location: Atlanta, GA
  • Phone:
  • URL: Zoom
  • Email:
  • Fee(s):
    N/A
  • Extras:
Contact
No contact information submitted.
Summaries

Summary Sentence: Statistical Viewpoints on network modeling and deep learning

Full Summary: No summary paragraph submitted.

Title: Statistical Viewpoints on network modeling and deep learning

 

Date: Nov 18th , 2022

Time: 8:00 - 9:00 AM EST

Meeting Link:

https://gatech.zoom.us/j/8833061674

 

Namjoon Suh

Machine Learning PhD Student

School of Industrial & Systems Engineering
Georgia Institute of Technology

 

Committee

1 Dr. Huo, Xiaoming (Advisor, ISyE, Gatech)

2 Dr. Mei, Yajun (Co-advisor, ISyE, Gatech)

3 Dr. Kang, Sung ha (Mathematics, Gatech)

4 Dr. Zhilova, Mayya (Mathematics, Gatech ) 

5 Dr. Zhou, Ding-Xuan (School of Mathematics and Statistics, The university of Sydney) 

 

Abstract

In my thesis presentation, two of my works will be presented:  

  1. A new statistical model for network data : We propose a combined model, which integrates the latent factor model and a sparse graphical model, for network data. It is noticed that neither a latent factor model nor a sparse graphical model alone may be sufficient to capture the structure of the data. The proposed model has a latent (i.e., factor analysis) model to represent the main trends (a.k.a., factors), and a sparse graphical component that captures the remaining ad-hoc dependence. Model selection and parameter estimation are carried out simultaneously via a penalized likelihood approach. The convexity of the objective function allows us to develop an efficient algorithm, while the penalty terms push towards low-dimensional latent components and a sparse graphical structure. The effectiveness of our model is demonstrated via simulation studies, and the model is also applied to four real datasets: Zachary's Karate club data,  Kreb's U.S. political book dataset (http://www.orgnet.com), U.S. political blog dataset, and citation network of statisticians; showing meaningful performances in practical situations. 
  2.  
  3. New insights in approximation theory and statistical learning rate of deep ReLU network: This work provides the rigorous theoretical analysis on how the approximation rate and learning rate (i.e., excess risk) behave when deep ReLU fully connected network is used as a function approximator (estimator) when ground-truth functions are assumed to be in Sobolev spaces defined over unit sphere. With the help of spherical harmonic basis, we track the explicit dependence on data dimension d in the rates and prove that deep ReLU net can avoid “the curse of dimensionality” when the function smoothness is in the order d as d tends to infinity. This discovery is not something observed in the state-of-the-art result in deep learning theory; specifically, when the function is defined on d-dimensional cube, or convolutional neural networks are used as the function approximator.   

Additional Information

In Campus Calendar
No
Groups

Graduate Studies

Invited Audience
Faculty/Staff, Public, Undergraduate students
Categories
Other/Miscellaneous
Keywords
Phd Defense
Status
  • Created By: Tatianna Richardson
  • Workflow Status: Published
  • Created On: Nov 11, 2022 - 12:01pm
  • Last Updated: Nov 11, 2022 - 12:02pm