Kuo-Wei Lai

Hello, my name is Kuo-Wei, and I am currently a third-year PhD student in the Department of Electrical and Computer Engineering (ECE) at Georgia Tech. I have the privilege of being advised by Prof. Vidya Muthukumar. Prior to joining Georgia Tech, I worked as a Research Assistant in the Department of Biomedical Engineering at Johns Hopkins University (JHU), under the guidance of Prof. Jeremias Sulam. At JHU, I earned my Master's degree in Robotics after completing my Bachelor's degree in the Department of Mechanical Engineering at National Taiwan University (NTU).

My research interests revolve around optimization problems within the fields of Machine Learning and Deep Learning. Lately, my focus has been particularly drawn to Implicit Bias and Out-of-Distribution (OOD) topics within learning theories.

• November 2024: I am honored to receive the ARC-ACO Fellowship (Spring 2025 cycle).
• April 2023: I am honored to receive the 2023 Outstanding ECE Graduate Teaching Assistant Award.

• Kuo-Wei Lai and Vidya Muthukumar: General loss functions lead to (approximate) interpolation in high dimensions. arXiv preprint [link].

• Kuo-Wei Lai and Vidya Muthukumar: Sharp analysis of out-of-distribution error for "importance-weighted" estimators in the overparameterized regime. ISIT 2024 [link].
• Kuo-Wei Lai, Manisha Aggarwal, Peter van Zijl, Xu Li and Jeremias Sulam: Learned proximal networks for quantitative susceptibility mapping. MICCAI 2020 [link] [github].

• Zhenghan Fang, Kuo-Wei Lai, Peter van Zijl., Xu Li and Jeremias Sulam: DeepSTI: Towards tensor reconstruction using fewer orientations in susceptibility tensor imaging. Medical image analysis [link].