LinkedIn GitHub Email Link

about me

My name is Katherine Tsai. I am a PhD student of Electrical and Computer Engineering at University of Illinois Urbana-Champaign and am currently a visiting student at Stanford University. I am advised by Dr. Sanmi Koyejo and working closely with Dr. Mladen Kolar. My research interests lie broadly at the intersections of machine learning, signal processing, and high-dimensional statistics. My PhD research focuses on developing principled methodologies to estimate graphs of stochastic processes, and to understand the complex interactions of dynamical systems like brain networks. I care about interpretability, reliability, and integrability in modeling designs and like to think about the underlying statistical and optimization problems. My research is mainly supported by NSF Graduate Research Fellowship. 

Previously, I completed the undergraduate degree at National Taiwan University and the master degree at University of Illinois Urbana-Champaign, both in Electrical Engineering. I spent a summer at Google Brain in 2022, working on adapting to distribution shifts using causal inference techniques.


journal publications

Latent Multimodal Functional Graphical Model Estimation

[ manuscript ] [ code ] [ arXiv ] [ poster ]

Katherine Tsai, Boxin Zhao, Sanmi Koyejo, Mladen Kolar

 Journal of the American Statistical Association (JASA), 2023

A Nonconvex Framework for Structured Dynamic Covariance Recovery

[ manuscript ]  [ code ]  [ arXiv ] [ poster ]

Katherine Tsai, Mladen Kolar, Sanmi Koyejo

Journal of Machine Learning Research (JMLR), 2022

Joint Gaussian graphical model estimation: A survey 

[ manuscript ]  [ arXiv ] 

Katherine Tsai, Sanmi Koyejo, Mladen Kolar

WIREs Computational Statistics, 2022

conferences and workshops

Proxy Methods for Domain Adaptation

[ arXiv ] [ poster ]

Katherine Tsai, Stephen R. Pfohl, Olawale Salaudeen,  Nicole Chiou, Matt J. Kusner, Alexander D'Amour, Sanmi Koyejo, Arthur Gretton 

International Conference on Artificial Intelligence and Statistics (AISTATS), 2024

Adapting to Latent Subgroup Shifts via Concepts and Proxies

[ manuscript ] [ code ]  [ arXiv

Ibrahim Alabdulmohsin, Nicole Chiou, Alexander D'Amour, Arthur Gretton, Sanmi Koyejo, Matt J. Kusner, Stephen R. Pfohl, Olawale Salaudeen, Jessica Schrouff, Katherine Tsai (in alphabetical order)

International Conference on Artificial Intelligence and Statistics (AISTATS), 2023

On Feasible Statistics of Graph Probabilistic Generative Models

[ arXiv ]

Pablo Robles-Granda, Katherine Tsai, Sanmi Koyejo

Machine Learning on Graphs (MLoG) Workshop, 2023