Varun Gupta

Hello! I am a graduate student in the Computer Science department at the University of Pennsylvania, where I am fortunate to be advised by Michael Kearns and Aaron Roth. Previously, I was an undergrad at Georgia Tech where I studied Computer Science and Public Policy.

My research is in machine learning and algorithmic game theory. I am interested in sequential online prediction, especially when involving strategic agents with competing incentives. I am also interested in studying these ideas with an eye towards trustworthy AI and robustness.

I enjoy talking with students about research so please get in touch if you want to discuss my work!

email: vgup@cis.upenn.edu

Research

Model Ensembling for Constrained Optimization. Joint with Ira Globus-Harris, Aaron Roth, Michael Kearns. Preprint.

Repeated Contracting with Multiple Non-Myopic Agents: Policy Regret and Limited Liability. Joint with Natalie Collina, Aaron Roth. EC 2024. Also accepted to 2024 ESIF Economics and AI+ML Meeting.

Multicalibrated Regression for Downstream Fairness. Joint with Ira Globus-Harris, Chris Jung, Michael Kearns, Jamie Morgenstern, Aaron Roth. AIES 2023.

Practical Adversarial Multivalid Conformal Prediction. Joint with Osbert Bastani, Chris Jung, Georgy Noarav, Ramya Ramalingam, Aaron Roth. NeurIPS 2022.

Online Multivalid Learning: Means, Moments, and Prediction Intervals. Joint with Chris Jung, Georgy Noarav, Mallesh Pai, Aaron Roth. ITCS 2022.

Adaptive Machine Unlearning. Joint with Chris Jung, Seth Neel, Aaron Roth, Saeed Sharifi-Malvajerdi, Chris Waites. NeurIPS 2021.