I recently obtained PhD of Electrical and Computer Engineering from the University of Illinois Urbana-Champaign and joined Apple. I was advised by Sanmi Koyejo and a member of Stanford Trustworthy AI Research Lab. My PhD thesis focuses on estimations and predictions in dynamical systems where data are collected in non-i.i.d. fashion. Specifically, I (i) developed efficient methods to estimate graphs from continuous time-series with guarantees and (ii) used the graphs to address distribution shifts problems. You can find my thesis here. My PhD research was supported by NSF Graduate Research Fellowship.
Previously, I completed my undergraduate degree at National Taiwan University and master degree at University of Illinois Urbana-Champaign, both in Electrical Engineering. During my graduate studies, I interned at the Brain team at Google and Intel AI lab.
High-dimensional Markov-switching Ordinary Differential Processes
[ arXiv ]
Katherine Tsai, Mladen Kolar, Sanmi Koyejo
2024+
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), 2024
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
Preference learning of Compound AI System
[ arXiv ]
Xiangwen Wang, Yibo Jacky Zhang, Zhoujie Ding, Katherine Tsai, Sanmi Koyejo
AAAI Multi-Agent AI in the Real World Workshop (AAAI MARW), 2025 (Oral)
Proxy Methods for Domain Adaptation
[manuscript] [code] [ 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
Graphical Models for High-dimensional Stochastic Processes: Estimation and Inference
[ thesis ]
Katherine Tsai, 2024
Let's chat