Scholar
Rajeev Verma
Google Scholar ID: xSgjaZYAAAAJ
PhD Student, University of Amsterdam
Citations & Impact
Citations
300
H-index
8
i10-index
6
Publications
20
Co-authors
0
Publications
Resume
Academic Achievements
- Published several papers including 'On Continuous Monitoring of Risk Violations under Unknown Shift' (UAI 2025), 'On Calibration in Multi-Distribution Learning' (ACM FAccT 2025), 'Learning to Defer to a Population: A Meta-Learning Approach' (AISTATS 2024, Oral, Student paper award (top 1%)), and 'Learning to Defer to Multiple Experts: Consistent Surrogate Losses, Confidence Calibration, and Conformal Ensembles' (AISTATS 2023).
Research Experience
- Extensive experience in studying the calibration properties of learning to defer (L2D) systems, extending L2D systems to allow for multiple experts, and studying the out-of-distribution behavior of L2D systems. Also collaborated on a project on the test-time adaption of L2D to new experts.
Education
- Studied Electrical Engineering at Indian Institute of Technology Patna (IITP) and Artificial Intelligence at the University of Amsterdam (UvA). Supervised by Eric Nalisnick and Christian A. Naesseth.
Background
- ELLIS PhD student with research interests in bridging the gap between prediction and decision-making, safe statistics, imprecise probabilities, and possibility theory.
Miscellany
- Reviewer for top conferences such as ICML (2023-2025), NeurIPS (2023), UAI (2024-2025), ICLR (2023), and ACL ARR (2024, 2025). Teaching assistant for courses like 'Human-in-the-Loop Machine Learning', 'Deep Learning 2', and 'Machine Learning 2'.