Anay Mehrotra
Postdoctoral Scholar, Management Science and Engineering
Bio
I am a Postdoctoral Scholar at Stanford, where I am excited to work with Amin Saberi. I completed my Ph.D. at Yale University where I was fortunate to be advised by Amin Karbasi and Manolis Zampetakis.
My research focuses on machine learning under complex conditions where traditional assumptions break down. My work has two parts. First, I develop foundations for machine learning with missing and selectively observed data (spanning causal inference, limited-dependence, truncated statistics, and omissions shaped by societal biases). Second, I study why generative AI systems (including language models) are effective and design methods to evaluate and improve their safety.
My work has received the Best Paper Award at COLT, been featured in WIRED, and received the Sir Binay Kumar Sinha award from IIT Kanpur. As an undergraduate, I represented IIT Kanpur at the ICPC World Final. While at Yale, I also taught at the Yale ICPC Club.
All Publications
-
Can SGD Select Good Fishermen? Local Convergence under Self-Selection Biases (Extended Abstract)
edited by Hanneke, S., Lattimore, T.
JMLR-JOURNAL MACHINE LEARNING RESEARCH. 2026: 3904-3905
View details for Web of Science ID 001863811600108
-
DDPM Score Matching and Distribution Learning
edited by Hanneke, S., Lattimore, T.
JMLR-JOURNAL MACHINE LEARNING RESEARCH. 2026: 1434-1435
View details for Web of Science ID 001863811600042
-
Language Generation with Infinite Contamination
edited by Hanneke, S., Lattimore, T.
JMLR-JOURNAL MACHINE LEARNING RESEARCH. 2026: 5053-5112
View details for Web of Science ID 001863811600137
-
Differentially Private Language Generation and Identification in the Limit (Extended Abstract)
edited by Hanneke, S., Lattimore, T.
JMLR-JOURNAL MACHINE LEARNING RESEARCH. 2026: 5113-5114
View details for Web of Science ID 001863811600138