About Me

I am a fifth year PhD student at University of Southern California studying Machine Learning in Yan Liu's Melady Lab. I graduated from The Ohio State University in 2020 with a double major in Computer Science and Mathematics. My currently research focuses on rooting the impressive representational power of deep neural networks with: high-dimensional statistics for theoretically grounded methods; interpretability for human-machine interaction and decision-making; and causality-based approaches for data-driven reasoning.

Research

The essence of my research direction is to make sense of the amazing power of deep neural networks. I am approaching this problem from a variety of different perspectives mainly focusing on interpretability, generalizability, statistical validity, and causality. My research statement and current directions can be viewed here. Some of my latest projects can be viewed here.

Publications

[Neurips 2022]   Sparse Interaction Additive Networks via Feature Interaction Detection and Sparse Selection
[ICPR 2021]    Hierarchical Classification with Confidence using Generalized Logits
[ISVC 2019]    Hierarchical Semantic Labeling with Adaptive Confidence

Projects