Published multiple papers in top conferences such as ICML, ICLR, NeurIPS, including 'Outliers with Opposing Signals Have an Outsized Effect on Neural Network Optimization' and '(Almost) Provable Error Bounds Under Distribution Shift via Disagreement Discrepancy'.
Research Experience
Spent two years as a software engineer at Google NYC working on Search Research and Machine Intelligence (SRMI). Currently a research scientist at Google Research.
Education
PhD student in the Machine Learning Department at CMU, advised by Andrej Risteski and Pradeep Ravikumar. Graduated from CMU with degrees in Computer Science and Statistics & Machine Learning, senior thesis advised by Manuel Blum and Santosh Vempala.
Background
Interested in the foundations of machine learning with a focus on robustness, reliability, and security. Emphasizes principled approaches to improving robustness and generalization, particularly under distribution shift or adversarial manipulation. Also frequently studies questions in representation learning.