[] | []

Xinyi Chen

xinyic@princeton.edu

I am a Ph.D. candidate in the Department of Computer Science at Princeton University, where I am very fortunate to be advised by Prof. Elad Hazan. Concurrently, I am a research scientist at Google DeepMind. Previously, I completed my undergraduate studies also at Princeton, in the Mathematics Department. I was generously funded by the NSF Graduate Research Fellowship and the Gordon Wu Fellowship from Princeton University.

My research is at the intersection of machine learning, optimization, and dynamical systems. I focus on developing provably robust and efficient methods for sequential decision-making and control, with applications in deep learning and quantum computing.

Preprints

Publications

Conference Publications

Online Control for Meta-optimization. NeurIPS 2023. Spotlight
With Elad Hazan.
Sketchy: Memory-efficient Adaptive Regularization with Frequent Directions. NeurIPS 2023.
With Vladimir Feinberg, Y. Jennifer Sun, Rohan Anil, and Elad Hazan.
Provable Regret Bounds for Deep Online Learning and Control. L4DC 2023.
With Edgar Minasyan, Jason D. Lee, and Elad Hazan.
Adaptive Online Learning of Quantum States. QIP 2023.
With Elad Hazan, Tongyang Li, Zhou Lu, Xinzhao Wang, and Rui Yang.
Robust Online Control with Model Misspecification. L4DC 2022.
With Udaya Ghai, Elad Hazan, and Alexandre Megretski.
Machine Learning for Mechanical Ventilation Control. (extended abstract) ML4H 2021.
With Daniel Suo, Udaya Ghai, Edgar Minasyan, Paula Gradu, Naman Agarwal, Cyril Zhang, Karan Singh, Julienne LaChance, Tom Zajdel, Manuel Schottdorf, Daniel Cohen, and Elad Hazan.
Black-Box Control for Linear Dynamical Systems. COLT 2021.
With Elad Hazan.
Online Agnostic Boosting via Regret Minimization. NeurIPS 2020.
With Nataly Brukhim, Elad Hazan, and Shay Moran.
Calibration, Entropy Rates, and Memory in Language Models. ICML 2020.
With Mark Braverman, Sham M. Kakade, Karthik Narasimhan, Cyril Zhang, and Yi Zhang.
Extreme Tensoring for Low-Memory Preconditioning. ICLR 2020.
With Naman Agarwal, Elad Hazan, Cyril Zhang, and Yi Zhang.
Efficient Full-Matrix Adaptive Regularization. ICML 2019. Tensorflow Optimizer
With Naman Agarwal, Brian Bullins, Elad Hazan, Karan Singh, Cyril Zhang, and Yi Zhang.
Online Learning of Quantum States. NeurIPS 2018 and QIP 2019.
With Scott Aaronson, Elad Hazan, Satyen Kale, and Ashwin Nayak.

Workshops

Onling Agnostic Boosting. Women in Machine Learning Workshop 2019. Oral Presentation.
With Nataly Brukhim, Elad Hazan, Shay Moran.

Journal Proceedings

Online Learning of Quantum States. Journal of Statistical Mechanics: Theory and Experiment, 2019.
With Scott Aaronson, Elad Hazan, Satyen Kale, and Ashwin Nayak.

Service

Area Chair: NeurIPS 2023
Program Committee: COLT 2021-23
General Co-Chair: Women in Machine Learning (WiML) Workshop 2020
Reviewer: NeurIPS (2020-22), ICML (2020-23), L4DC, AISTATS, JMLR, TMLR

Talks

Provable Regret Bounds for Deep Online Learning and Control.
- Google Research Learning Theory Workshop, Virtual. October 2021.
Black-Box Control for Linear Dynamical Systems.
- Google Research Diff-everything Workshop, Virtual. September 2021.
- Conference on Learning Theory, Boulder, CO, USA. August 2021.
- RL Theory Virtual Seminars, November 2020.
Online Agnostic Boosting via Regret Minimization.
- Google Research Conference, Mountain View, CA, USA. February 2020.
- MSR New England ML Lunch, Boston, MA, USA. January 2020.
- WiML, Vancouver, BC, Canada. December 2019.
Efficient Full-Matrix Adaptive Regularization.
- International Conference on Machine Learning, Long Beach, CA, USA. June 2019.
Online Learning of Quantum States.
- Princeton Algorithm and Machine Learning Seminar, Princeton, NJ, USA. September 2018.