Karan Singh

Karan Singh is an Assistant Professor of Operations Research at the Tepper School of Business, Carnegie Mellon University. His work bridges machine learning and optimization, focusing on algorithmic solutions for interactive learning paradigms such as reinforcement learning and online control.

• Education: PhD in Computer Science (Princeton University, 2022), MA in Computer Science (Princeton, 2017), BTech in Computer Science (IIT Kanpur, 2015)

His research addresses computational and statistical challenges in feedback-driven learning systems, with key contributions in algorithmic reductions, nonstochastic control, and privacy-preserving online optimization. Recent work includes developing sample-efficient boosting methods and establishing regret bounds for differentially private learning.

Notable scientific achievements include the Porter Ogden Jacobus Fellowship (Princeton's highest graduate honor), a Best Paper Award at the OptRL workshop (NeurIPS 2019), and a Spotlight Prize at the New York Academy of Sciences' ML Symposium (2018).

Karan actively contributes to academic service as a reviewer for International Conference on Machine Learning (ICML), NeurIPS, and Mathematics of Operations Research. He serves on CMU committees including the Business Analytics Teaching Track Search Committee and Special Taskforce for Testing Requirements.