About me

I’m Chanwoo Park. I am a first-year Ph.D. student at MIT EECS & LIDS, advised by Asu Ozdaglar. I am closely working with Kaiqing Zhang.

My current research interests are:

• Intersection of (Multi-agent) Reinforcement Learning Theory, Game Theory, and Statistics
• Deep Learning Theory: Self Supervised Learning and Diffusion Model
• Equivariant Neural Networks (RL, DL)

Fortunately, as an undergraduate student, I worked with Prof. Taesung Park and Prof. Ernest K. Ryu at Seoul National University. Also, I did a research internship in NAVER AI Lab, advised by Sangdoo Yun and Sanghyuk Chun. I researched Deep Learning Theory with Computer Vision.

I am supported by Korea Foundation for Advanced Studies. Super thanks!

I am holding the certification in Korean actuary since 2018.

I run ML-Theory-Korea with my colleagues. I like to talk about the theory or application of deep learning (diffusion model, prompt learning…) and (multi-agent) reinforcement learning. Feel free to email me (cpark97 at mit.edu). We are actively researching on several areas.

News

• September 2022: Paper on a Loss function perspective of mixed sample data augmentation accepted at NeurIPS 2022. This work was done when I was intern in NAVER AI Lab. I got NeurIPS travel awards!
• September 2022: I started my PhD at MIT! I also got Xianhong Wu Fellowship from MIT.
• July 2022: I am married!! Excited for my new life.
• June 2022: Paper on a Lyapunov analysis of Optimized Gradient Methods accepted at Applied Mathematics and Optimization.
• May 2022: Paper on a deep learning based pathway analysis (DeepHisCoM) accepted at Briefings in Bioinformatics.
• January 2022: Started internship in NAVER AI Lab (Mentor: Sangdoo Yun).
• December 2021: Started ML-Theory-Korea with my colleagues.
• September 2021: Paper on a geometric structure of acceleration methods accepted at NeurIPS 2021.
• December 2020: First place on Simon Marais Mathematics Competition (Pair Session)

Contact

Email: cpark97[at]mit.edu