About me
I am a final-year Ph.D. student in the Department of Statistics at UC Berkeley, advised by Ryan Tibshirani and Giles Hooker. Starting this summer, I’ll be a Research Scientist at BlackRock AI Labs, working with Stanford professors Stephen Boyd, Emmanuel Candes, Trevor Hastie, and Mykel Kochenderfer. I completed my B.S. at Yale University, where I did NLP research with the late Dragomir Radev.
During my Ph.D., I interned in the computer vision group at Apple, designing interpretability methods to analyze failure modes of FaceID, and at Genentech on computational pathology. Before Berkeley, I worked on speech recognition at a startup in Israel.
Research Interests
My research aims to ensure the safe and effective deployment of machine learning. To that end, my work on black-box interpretability enhances the reliability of SHAP and LIME, and introduces new techniques to understand image models. I also work on uncertainty quantification, with particular focus on rankings and time series.
While I am broadly interested in ML for health, my current applied emphasis is in epidemiology. Through the Delphi Group, I construct analytical and algorithmic tools to track infectious disease risks as they unfold in real-time.
Please feel free to reach out if you’d like to connect!
News
- Oct 2025. Estimating Time-Varying Epidemic Severity Rates with Adaptive Deconvolution is up on Arxiv.
- Aug 2025. Gaussian Rank Verification published in Stat.
- July 2025. Unifying Image Counterfactuals and Feature Attributions with Latent-Space Adversarial Attacks presented in the Actionable Interpretability Workshop at ICML.
- July 2025. Statistical Significance of Feature Importance Rankings shared at UAI in Rio. Our methods stabilize SHAP, LIME, and other interpretability methods using ideas from Gaussian Rank Verification.