I'm interested in deep learning, generative modeling, and out-of-distribution detection and generalization. I'm particularly interested in applications of machine learning for health and science.
Previously, I worked on machine learning problems in industry, notably in NLP, information extraction, and document processing.
Feel free to contact me for research collaborations or other engagements.
- Lily H. Zhang, Mark Goldstein, Rajesh Ranganath. Understanding Out-of-distribution Detection with Deep Generative Models. ICML, 2021.
- Aahlad Puli, Lily H. Zhang, Eric Oermann, Rajesh Ranganath. Out-of-Distribution Generalization in the Presence of Nuisance-Induced Spurious Correlations. ICLR, 2022.
- Lily H. Zhang, Veronica Tozzo, John M. Higgins, Rajesh Ranganath. Set Norm and Equivariant Residual Connections: Putting the Deep in Deep Sets. ICML, 2022.
- Lily H. Zhang, Mark Goldstein, Rajesh Ranganath. Understanding Out-of-distribution Detection with Deep Generative Models. ICLR RobustML Workshop, 2021.
- Lily H. Zhang, Michael Hughes. Rapid Model Comparison by Amortizing Across Models. Proceedings of The 2nd Symposium on Advances in Approximate Bayesian Inference, 2020.
- New York University, New York, NY. Candidate for Doctor of Philosophy in Data Science. Advisors: Rajesh Ranganath, Kyle Cranmer. Aug. 2020 – Present
- Harvard College, Cambridge, MA. Bachelor of Arts in Statistics and Computer Science. Magna Cum Laude with High Honors. Aug. 2013 – May 2017
Honors & Awards
- DeepMind Fellow, 2020.
- Phi Beta Kappa, 2017.