Rajeev Verma

PhD Student, AMLab & Delta Lab, University of Amsterdam
rajeev.ee15@gmail.com · GitHub · Twitter · LinkedIn

I'm an ELLIS PhD student at the University of Amsterdam (UvA), where I'm a part of the AMLab and Delta Lab. Previously, I studied Electrical Engineering at the Indian Institute of Technology Patna (IITP) and Artificial Intelligence at the University of Amsterdam (UvA).

I'm generally interested in bridging the gap between prediction and decision-making, especially in the context of the institutional separation between model designers and decision-makers. I'm also interested in safe statistics, imprecise probabilities, and possibility theory.

Previously, I worked on studying the calibration properties of learning to defer (L2D) systems [ICML'22], extending L2D systems to allow for multiple experts [AISTATS'23], and studying the out-of-distribution behavior of L2D systems (in preparation). I also collaborated on a project on the test-time adaption of L2D to new experts [AISTATS'24].

I bridge philosophy, mathematics, and policy.

Blog

Notes from the underground — a running blog of my most-random thoughts.
No sure loss, calibration, and insurance.
What are good forecasts?
A relativistic perspective of uncertainty in machine learning. Note: A part of this appeared at the ICML 2026 Workshop on Philosophy Meets Machine Learning: What Counts As Trustworthy? as A Relativistic Perspective of Reliability in Machine Learning, that was invited for an in-person oral talk.

Selected Publications

(* Denotes equal contribution)

Ongoing & Workshop Articles

Avoiding the Tragedy of the Commons in AI Regulation via Dynamic Licensing Rajeev Verma, Anurag Singh, Christian A. Naesseth, Eric Nalisnick, Krikamol Muandet ICLR 2026 Workshop on AI for Mechanism Design and Strategic Decision Making (AIMS)
So What are Good Imprecise Forecasts? Rajeev Verma^*, Rabanus Derr^*, Christian A. Naesseth, Volker Fischer, Eric Nalisnick Workshop on Epistemic Intelligence in Machine Learning (EurIPS 2025)

Conference Papers & Thesis

Boosting for Predictive Sufficiency Abbavaram Gowtham Reddy, Rajeev Verma, Celia Rubio-Madrigal, Krikamol Muandet, Rebekka Burkholz ICLR 2026
On Continuous Monitoring of Risk Violations under Unknown Shift Alexander Timans^*, Rajeev Verma^*, Eric Nalisnick, Christian A. Naesseth UAI 2025 · [talk]
On Calibration in Multi-Distribution Learning Rajeev Verma, Volker Fischer, Eric Nalisnick ACM FAccT 2025 Note: Also gave an invited talk at the 2nd Workshop on Learning Under Weakly Structured Information.
Learning to Defer to a Population: A Meta-Learning Approach Dharmesh Tailor, Aditya Patra, Rajeev Verma, Putra Manggala, Eric Nalisnick AISTATS 2024 · Oral, Student paper award (top 1%)
Learning to Defer to Multiple Experts: Consistent Surrogate Losses, Confidence Calibration, and Conformal Ensembles Rajeev Verma^*, Daniel Barrejón^*, Eric Nalisnick AISTATS 2023 Note: Also appeared at the ICML 2022 Workshop on Human-Machine Collaboration and Teaming as On the Calibration of Learning to Defer to Multiple Experts.
Calibrated Learning to Defer with One-vs-All Classifiers Rajeev Verma, Eric Nalisnick ICML 2022
On the Calibration of Learning to Defer Systems Rajeev Verma Master's Thesis 2022 (UvA) · [talk] [UvA News]

Service

Reviewer

ICML (Gold reviewer, 2026), NeurIPS (Top reviewer, 2023), UAI, ICLR, ACL

Teaching

Human-in-the-Loop Machine Learning (Teaching Assistant)
Deep Learning 2 (Teaching Assistant)
Machine Learning 2 (Teaching Assistant)