Apurv Shukla
Apurv’s research focuses on problems in energy markets and platform economies with a particular focus on designing algorithmic frameworks for decision-making in dynamic environments when learning agents are constrained by information asymmetry, preference heterogeneity, and privacy. Previously, he was at University of Michigan, Ann Arbor and Texas A&M. He earned his PhD from Columbia University.
His representative publications are:
- Generalized Quantal Response Equilibria: Existence and Efficient Learning preprint
with Vijay Subramanian, Andy Zhao and Rahul Jain - Preference-based Pure Exploration preprint
NeurIPS 2024 with Debabrota Basu - Vector preference-based contextual bandits under distributional shifts prerpint
with P.R. Kumar - Differentially Private Online Resource Allocation with P.R. Kumar
- Sample Complexity of Chance Constrained Optimization in Dynamic Environment preprint
ACC 2024 with Qian Zhang and Le Xie - Robust Streaming PCA preprint
NeurIPS 2022 with Daniel Bienstock, Minchan Jeong and Seyoung Yun
Teaching
- Co-Instructor, Data Sciences and Applications for Modern Power Systems, Fall 2023