
Director of S2ML lab. Associate Professor at UCSD (2024 - now). Previously associate professor at UCSB (2018-2023) and Amazon Web Services (2017-2018). Yu-Xiang received his PhD 2017 from the Machine Learning Department at Carnegie Mellon University (CMU). His research interests include on statistical theory and methodology, differential privacy, large-scale machine learning, reinforcement learning and deep learning.
Postdoc(coadvised with Kamalika Chaudhuri). Ruihan works on privacy, online learning and large language models.
PhD Student. Dan's research focuses on reinforcement learning, differential privacy and deep learning optimization. He has done some work about low-adaptive (batched) RL and differentially private RL in both online and offline settings. Currently, Dan is developing a modern theory for deep learning.

PhD student. Sunil is working on reinforcement learning, adaptive nonparametric regression and diffusion models.

PhD student. Erchi is working on differentially private tree-boosting with applications to healthcare. He is also interessted in theory of private learning.

PhD Student (coadvised with Rahul Parhi and Alex Cloninger). Tongtong's research focuses on the mathematics of deep learning, in particular, generalization under the Edge-of-stability.
PhD Student (coadvised with Kamalika Chaudhuri). Pengrun works on memorization and watermarking in LLMs.

PhD in CS (2023). Dheeraj worked on online learning under non-staionarities and non-parametric regression / forecasting, as well as online adaptation to distribution-shifts in deep learning. He received Best Student Paper from COLT'21. Currently Dheeraj works at Amazon as an Applied Scientist.
PhD in CS (2023). Now Experiential AI Postdoctoral Fellow at Northeastern University. Rachel worked on differential privacy and differentially private machine learning.

PhD in CS (2023). Chong worked on Bayesian optimization, bandits, active learning as well as adaptive algorithms for data-driven new material discovery. Now Assistant Professor of Computer Science at University at Albany - State University New York.
PhD in CS (2023). Now research scientist at TikTok. Yuqing worked on modern accounting methods for differential privacy and private learning. Yuqing is a main contributor to autodp.

PhD in Statistics (2023); PhD in CS (2023). Now postdoc at Princeton University. Ming worked on offline policy evaluation and learning in reinforcement learning.

PhD in CS (2024). Now postdoc at Berkeley. Xuandong worked on responsible use of generative AI, e.g., watermarking, copyright, security, and privacy. He earned his B.S. in Computer Science from Zhejiang University in 2019. Xuandong is a recipient of the Chancellor's Fellowship from UC Santa Barbara.

PhD in CS (2024). Now postdoc at Carnegie Mellon. Jianyu worked on on-line learning and bandits, with specialization in dynamic pricing.

PhD Student in UCSD CSE. Esha worked on understanding the optimization and generalization of neural networks.

MS in CS (2024). Momin worked on online and offline reinforcement learning with applications to computer networking. Joined University of Virginia (UVA) as a PhD student.

PhD in ECE (2023). Now scientist at Huawei. Kaiqi worked on the theory of deep learning.