Xinyi Chen

I’m a research engineer at Google AI. I’m interested in algorithms in machine learning, specifically online learning and nonconvex optimization. I graduated from the math department at Princeton University, where I was fortunate to be advised by Prof. Elad Hazan.


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.


Calibration, Entropy Rates, and Memory in Language Models.
With Mark Braverman, Sham M. Kakade, Karthik Narasimhan, Cyril Zhang, and Yi Zhang.

Extreme Tensoring for Low-Memory Preconditioning.
With Naman Agarwal, Elad Hazan, Cyril Zhang, and Yi Zhang.


On Second Order Methods in Optimization for Machine Learning. Undergraduate Thesis. Middleton Miller ‘29 Prize for Best Thesis.
Advised by Prof. Elad Hazan.