Date: Monday, July 29th, 2024

Time: 3:00PM-5:00PM EST (12:00 PM to 2:00 PM PST)

Location and remote link: Coda C0915 Atlantic, (https://gatech.zoom.us/j/6943444592?pwd=b7kidU38Qn66epIlqa805MGu6QZyyU.1)

Tianrong Chen

ECE PhD Student

Georgia Institute of Technology

Committees:

1. Dr. Evangelos Theodorou (School of Aerospace Engineering, Georgia Tech; Advisor)
2. Dr. Matthieu Bloch (School of Electrical and Computer Engineering, Georgia Tech; Co-Advisor)
3. Dr. Justin Romberg (School of Electrical and Computer Engineering, Georgia Tech) 
4. Dr. Molei Tao (School of Mathematics, Georgia Tech)
5. Dr. Yao Xie (School of Industrial and Systems Engineering, Georgia tech)
6. Dr. Shuangfei zhai (Apple Machine Learning Research)

Abstract:

Generative models have gained significant popularity in recent years, and Stochastic Optimal Control soc has also advanced rapidly in parallel. This thesis addresses the problem of understanding dynamical generative models from the perspective of Stochastic Optimal Control, thereby providing insights from the well-established Stochastic Optimal Control theory. Additionally, it explores the challenges of high-dimensional Stochastic Optimal Control by leveraging deep learning techniques. Through this dual approach, the research aims to enhance the theoretical understanding and practical application of generative models and Stochastic Optimal Control in complex, high-dimensional environments.