A photo of me

About Me

I'm an ELLIS PhD student at AMLab / Delta Lab supervised by Eric Nalisnick and Christian A. Naesseth. Previously, I studied Electrical Engineering at the Indian Institute of Technology Patna (IITP) and Artificial Intelligence at the University of Amsterdam (UvA).

Email | Google Scholar | Github | Twitter | Linkedin

Research Interests

My general research interests are in AI safety and responsible AI, aiming to build systems that are maximally useful to society with provable guarantees. In my current research, I'm working at the intersection of uncertainty quantification and decision making. I'm studying the calibration properties induced by minimizing generalized risk measures as an aggregation mechanism. 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].

Selected Publications

 (* Denotes equal contribution)