About
I am a Masters student at Columbia University, NYC, studying Computer Science (Machine Learning track). I expect to graduate in December 2022.
I am keenly interested in causal inference and its (as yet under-explored) intersections with reinforcement learning, decision theory and probabilistic ML. I am particularly interested in ensuring AI systems are aligned with human values.
Previously, I worked in corporate banking in the UK and Singapore. I have publicly signed the Giving What We Can pledge to contribute >10% of my income to charity until retirement.
Research
Avoiding Calvinist Decision Traps Using Structural Causal Models [pdf]
Arvind Raghavan
NeurIPS22 – 36th Conference on Neural Information Processing Systems (ML Safety Workshop), 2022
Optimal and Stable Decision Strategies in Multi-Agent Problems with Generalized Multi-Arm Bandits [pdf]
Arvind Raghavan, Elias Bareinboim
Working Paper, 2022
CausalEXP3 – An Efficient Causal Algorithm for Adversarial Bandits [pdf]
Arvind Raghavan
Working Paper, 2022
Human Evaluation of Text-to-Image Models on a Multi-Task Benchmark [pdf]
Vitali Petsiuk, Alexander Siemenn, Saisamrit Surbehera, Zad Chin, Kieth Tyser, Gregory Hunter, Arvind Raghavan, Yann Hicke, Bryan Plummer, Ori Kerret, Tonio Buonassisi, Kate Saenko, Armando Solar-Lezama, Iddo Drori
NeurIPS22 – 36th Conference on Neural Information Processing Systems (Workshop on Human Evaluation of Generative Models), 2022 – Oral
A Dataset for Learning University STEM Courses at Scale and Generating Questions at a Human Level (accepted)
Iddo Drori, Sarah Zhang, Zad Chin, Reece Shuttleworth, Albert Lu, Linda Chen, Bereket Birbo, Michele He, Pedro Lantigua, Sunny Tran, Gregory Hunter, Bo Feng, Newman Cheng, Roman Wang, Yann Hicke, Saisamrit Surbehera, Arvind Raghavan, Alexander Siemenn, Nikhil Singh, Jayson Lynch, Avi Shporer, Nakul Verma, Tonio Buonassisi and Armando Solar-Lezama
AAAI23 – 13th AAAI Symposium on Educational Advances in Artificial Intelligence, 2023