Shipra Agrawal is Cyrus Derman Assistant Professor of the Department of Industrial Engineering and Operations Research. She is also affiliated with the Department of Computer Science and the Data Science Institute, at
Columbia University. She received her PhD in Computer Science from Stanford University in June 2011 under the guidance of Prof. Yinyu Ye,
and was a researcher at Microsoft Research India from July 2011 to August 2015. Her research spans several areas of optimization and machine learning,
including online optimization under uncertainty, multi-armed bandits, online learning, and reinforcement learning. She is also interested in
prediction markets and game theory.
Shipra serves as an associate editor for Management Science (Optimization area)
and Mathematics of Operations Research (Learning theory area) and INFORMS Journal on Optimization.
Her research is supported by a
Google Faculty research award (2017), Amazon research award (2017),
and an NSF CAREER Award.
For further information, please see CV .
(A full list of journal and conference papers is here )
Reinforcement Learning for Integer Programming: Learning to Cut, Y. Tang, S. Agrawal, Y. Faenza, ICML 2020. [arXiv]
Learning in structured MDPs with convex cost functions: Improved regret bounds for inventory management. S. Agrawal and R. Jia, EC 2019. [arXiv]
Robust Repeated Auctions under Heterogeneous Buyer Behavior. S. Agrawal, C. Daskalakis, V. Mirrokni, B. Sivan, EC 2018. [ arXiv ]
Optimistic posterior sampling for reinforcement learning: worst-case regret bounds. S. Agrawal and R. Jia, NIPS 2017 (spotlight) [ arXiv ]
Thompson Sampling for MNL-bandit. S. Agrawal, V. Avandhanula, V. Goyal, A. Zeevi. COLT 2017. [ arXiv ]
Fast algorithms for online stochastic convex programming. S. Agrawal, N. R. Devanur. SODA 2015. [ EE ] [ arXiv ]
Bandits with concave rewards and convex knapsacks. S. Agrawal, N. R. Devanur. EC 2014. [ EE ] [ arXiv ]
Thompson Sampling for contextual bandits with linear payoffs. S. Agrawal, N. Goyal. ICML 2013. [ pdf ] [Newer version with improved results: arXiv ]
Analysis of Thompson Sampling for the multi-armed bandit problem. S. Agrawal, N. Goyal. COLT 2012. [ pdf ] [ arXiv ]