I’m interested in exploring fundamental questions behind tools in modern machine learning and using them to develop new, theoretically grounded methods. My current interests revolve around how to encode and evaluate sources of supervision and side information throughout the ML pipeline (e.g. weakly/semi/self-supervised) through both information-theoretic and geometric lenses. In particular, my work in graduate school so far has applied this interest to latent variable graphical models, distribution shift, and representations learned via contrastive losses.
Previously, I graduated summa cum laude from Princeton University in 2019 with a concentration in Operations Research and Financial Engineering (ORFE) and a certificate in Applications of Computing. I worked on my senior thesis on quantum machine learning with Prof. Elad Hazan and completed junior independent work on modeling misinformation in social networks with Prof. Miklos Racz.
Publications and Preprints
The Details Matter: Preventing Class Collapse in Supervised Contrastive Learning
Daniel Y. Fu*, Mayee F. Chen*, Michael Zhang, Kayvon Fatahalian, and Christopher Ré. AAAI Workshop on Artificial Intelligence with Biased or Scarce Data, 2022.
TABi: Type-Aware Bi-encoders for End-to-End Entity Retrieval
Megan E. Leszczynski, Daniel Y. Fu, Mayee F. Chen, and Christopher Ré. In submission, 2021.
An Adversarial Model of Network Disruption: Maximizing Disagreement and Polarization in Social Networks.
Mayee F. Chen and Miklos Z. Racz. IEEE Transactions on Network Science and Engineering (TNSE), 2021.
paper | code
Mandoline: Model Evaluation under Distribution Shift
Mayee F. Chen*, Karan Goel*, Nimit Sohoni*, Fait Poms, Kayvon Fatahalian, and Christopher Ré. International Conference on Machine Learning (ICML), 2021.
paper | code | slides
Comparing the Value of Labeled and Unlabeled Data in Method-of-Moments Latent Variable Estimation.
Mayee F. Chen*, Benjamin Cohen-Wang*, Steve Mussmann, Frederic Sala, and Christopher Ré. Artificial Intelligence and Statistics (AISTATS), 2021.
paper | slides
Train and You’ll Miss It: Interactive Model Iteration with Weak Supervision and Pre-Trained Embeddings.
Mayee F. Chen*, Daniel Y. Fu*, Frederic Sala, Sen Wu, Ravi Teja Mullapudi, Fait Poms, Kayvon Fatahalian, and Christopher Ré. arXiv preprint arXiv:2006.15168, 2020.
paper | code | video
Fast and Three-rious: Speeding Up Weak Supervision with Triplet Methods.
Daniel Y. Fu*, Mayee F. Chen*, Frederic Sala, Sarah M. Hooper, Kayvon Fatahalian, and Christopher Ré. International Conference on Machine Learning (ICML), 2020.
paper | code | video | blog
Effect of Rotational Grazing on Plant and Animal Production.
Mayee F. Chen and Junping Shi. Journal of Mathematical Biosciences and Engineering, vol. 15, no. 2. 2018.
paper | slides
Efficient GCD Computation for Big Integers on Xeon Phi Coprocessor.
Jie Chen, William Watson, and Mayee F. Chen. IEEE Conference on Networking, Architecture, and Storage (NAS). 2014.
paper | slides