Scholar
aahlad puli
Google Scholar ID: xWmCmBQAAAAJ
Faculty Fellow in Data Science, NYU
Citations & Impact
Citations
524
H-index
12
i10-index
12
Publications
20
Co-authors
0
Contact
Publications
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
- Two papers at NeurIPS 2024; Successfully defended PhD dissertation; Published 'Nuisances via Negativa' in TMLR; Gave a talk on OOD generalization in health at INFORMS; Paper accepted at NeurIPS 2023; Organized SCIS workshop at ICML 2023; Published 'DIET' at AISTATS; Recipient of Apple Scholars in AI/ML PhD Fellowship; Published 'NuRD' at ICLR 2022; Named Rising Star by the Trustworthy ML initiative; Published 'CONTRA: Contrarian statistics for controlled variable selection' at AISTATS 2021; Multiple papers at NeurIPS 2020.
Research Experience
- Intern at Adobe Research, working on Bayesian attribution models; Software Developer at DBMI, Columbia University; Worked in the Clinical Machine Learning group at NYU, mentored by Prof. Uri Shalit and Prof. David Sontag.
Education
- PhD in Computer Science from the Courant Institute, NYU, advised by Prof. Rajesh Ranganath; MS in CS from NYU, 2017.
Background
- Currently a Faculty Fellow at the Center for Data Science, NYU. Research interests include closing the gap between how models are built and how they will be used, focusing on out-of-distribution generalization, causality, interpretability, and feature learning. Current work aims to improve feature learning in ML models by studying and mitigating the role of gradients in overfitting. Earlier work focused on making models generalize across different populations, informed by insights and techniques from causal inference. Primary application area is AI for healthcare (e.g., medical image classification and survival analysis), with an interest in ML for science in general.
Miscellany
- Eternally excited about new ideas and finding good applications for his work.
Co-authors