image

Email: JerryChee [at] cs.cornell.edu

CV / Google Scholar / ArXiv

I am in the final year of my PhD. I am looking for applied science positions in industry!


About

I am a Ph.D. student in Computer Science at Cornell University, advised by Chris De Sa. I am interested in making machine learning work for practitioners. I am currently working on quantization methods for large-scale models such as LLMs. My work on ``incoherence processing’’ is emegering as an important tool in achieving <=4 bit quantizationin LLMs.

I have collaborated with industry and scientific practitioners across a diverse array of fields, including deep noise suppression at Microsoft, economic causal modeling at Amazon, safe recommender systems at Meta, and plant geneticists at Cornell. I have developed novel methodologies across deep learning compression, scalable statistical inference, safe recommender systems, etc.

In my previous professional life I worked as a data scientist consultant at McKinsey & Company. I graduated from the University of Chicago in 2017 with a degree in Computational and Applied Mathematics, where I worked with Panos Toulis at UChicago Booth on statistically motivated topics in stochastic gradient descent (SGD).


Publications

QuIP#: Even Better LLM Quantization with Hadamard Incoherence and Lattice Codebooks
Albert Tseng, Jerry Chee, Qingyao Sun, Volodymyr Kuleshov, Chris De Sa
In ICML 2024
[Proceedings] [ArXiv] [Code]

Harm Mitigation in Recommender Systems under User Preference Dynamics
Jerry Chee, Shankar Kalyanaraman, Sindhu Ernala, Udi Weinsberg, Sarah Dean, Stratis Ioannidis
In KDD 2024
[ArXiv]

QuIP: 2-Bit Quantization of Large Language Models With Guarantees
Jerry Chee, Yaohui Cai, Volodymyr Kuleshov, Chris De Sa
In NeurIPS 2023, Spotlight
[Proceedings] [Arxiv] [Code]

“Plus/minus the learning rate”: Easy and Scalable Statistical Inference with SGD
Jerry Chee, Hwanwoo Kim, Panos Toulis
In AISTATS 2023
[Proceedings]

Model Preserving Compression for Neural Networks
Jerry Chee, Megan Renz, Anil Damle, Chris De Sa
In NeurIPS 2022
[Proceedings] [ArXiv]

Performance Optimizations on U-Net Speech Enhancement Models
Jerry Chee, Sebastian Braun, Vishak Gopal, Ross Cutler
In IEEE MMSP 2022
[Proceedings] [ArXiv]

How Low Can We Go: Trading Memory for Error in Low-Precision Training
Chengrun Yang, Ziyang Wu, Jerry Chee, Chris De Sa, Madeleine Udell
In ICLR 2022
[Proceedings] [ArXiv]

Understanding and Detecting Convergence for Stochastic Gradient Descent
Jerry Chee, Ping Li
In IEEE Big Data 2020
[Proceedings] [ArXiv]

Convergence diagnostics for stochastic gradient descent with constant step size
Jerry Chee, Panos Toulis
In AISTATS 2018, Oral Presentation (5%)
[Proceedings] [ArXiv]