Rajeev Verma

PhD candidate (advised by Eric Nalisnick and Volker Fischer)
AMLab, Delta Lab
Informatics Institute
University of Amsterdam
Science Park, Lab 42, L4.60

 

Personal page   Google scholar   Github   Twitter  

I am a PhD student in Machine Learning at Amsterdam Machine Learning Lab (AMLab) and Delta Lab, supervised by Eric Nalisnick and Volker Fischer. My research interests are in AI safety and aim to build systems that are maximally useful to the society with provable guarantees. Specifically, I am excited about human-AI compatibility and complementarity, uncertainty quantification and decision making especially in case of imprecise, vague, or conflicting information.


Selected Publications

  1. AISTATS
    Learning to Defer to Multiple Experts: Consistent Surrogate Losses, Confidence Calibration, and Conformal Ensembles
    In Proceedings of the 26th International Conference on Artificial Intelligence and Statistics (AISTATS) 2023
    PDF
  2. ICML
    Calibrated Learning to Defer with One-vs-All Classifiers
    Verma, Rajeev, and Nalisnick, Eric
    In Proceedings of the 39th International Conference on Machine Learning (ICML) 2022
    PDF