Shipra Agrawal

Associate Professor
Industrial Engineering and Operations Research
Member, Data Science Institute (DSI)
Affiliate, Department of Computer Science
Columbia University
Office: Mudd 423 Phone: 212 853 0684

Brief Bio

Shipra Agrawal is an Associate Professor of the Department of Industrial Engineering and Operations Research at Columbia University. She is also affiliated with the Department of Computer Science and the Data Science Institute. 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 and Mathematics of Operations Research, INFORMS Journal on Optimization and Journal of Machine Learning Research (JMLR). 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 .

PhD Students

  • Priyank Agrawal
  • Sudeep R. Putta
  • Steven Yin
  • Yunhao Tang (Graduated 2021, research scientist at Google Deepmind London)
  • Xingyu Zhang (Graduated 2021, research scientist at Amazon)
  • Randy Jia (Graduated 2020, research scientist at Amazon)
  • Mohammad Shadravan (Graduated 2020)
  • Vashist Avadhanula (Graduated 2018, research scientist at Facebook)

    Selected Publications

    (A full list of journal and conference papers is here )
    • Dynamic pricing and learning under Bass model, S. Agrawal, S. Yin, A. Zeevi, EC 2021. [arXiv]
    • Dynamic first price Auctions robust to heterogeneous buyers, S. Agrawal, E. Balkanski, V. Mirrokni, B. Sivan, EC 2021. [arXiv]
    • On optimal ordering in the optimal stopping problem, S. Agrawal, J. Sethuraman, X. Zhang. EC 2020. [arXiv]
    • 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 ]
    • Near-Optimal Regret Bounds for Thompson Sampling JACM 64 Issue 5, October 2017 [ EE ][ pdf ].
      (The pdf version here includes a correction made to the published version: in Lemma 2.13, page 15:16. Modified text is in blue)
    • Thompson Sampling for contextual bandits with linear payoffs. S. Agrawal, N. Goyal. ICML 2013. [ EE ] [Newer version with improved results is here: arXiv ]
    • Analysis of Thompson Sampling for the multi-armed bandit problem. S. Agrawal, N. Goyal. COLT 2012. [ pdf ] [ arXiv ]


    Some recent professional activities

    • Co-Chair, INFORMS Nicholson Prize Committee, 2019.
    • Associate Editor: Mathematics of Operations Research (Learning theory area), Management Science (Optimization area), INFORMS Journal on Optimization and Journal of Machine Learning Research (JMLR).
    • Committees: ICML 2021 (Area Chair), NeurIPS 2020 (Area Chair), ICML 2020 (Area Chair), COLT 2020 (SPC), IJCAI 2020 (SPC) AAAI 2020 (SPC), ICML 2019 (Area Chair), COLT 2017-2019 (PC), SODA 2019 (PC), ITCS 2018 (PC), RANDOM 2017(PC), WWW 2017 (PC)
    • Co-organizer NYC Data Science DS3 seminar series


    Contact Information

      Mudd Building, Office 423
      500 West 120th Street
      New York, NY 10027


    • Title: A tutorial on multi-armed bandits at Simons Institute, Berkeley, CA. Aug 22, 2022.
    • Title: Dynamic Pricing and Learning under the Bass model, July 19, 2021.
    • Title: "Recent advances in multiarmed bandits for sequential decision making"
      Tutorial in OR at at INFORMS annual meeting 2019

    • Title: Learning MDPs with convex cost functions: improved regret bounds for inventory management
      at NeurIPS 2019 Workshop on Optimization foundations of Reinforcement Learning

      ( my talk begins at 37:33 )

  • News and Events
    • Sep 12 Invited talk at IEOR Berkeley.
    • Aug 22 A tutorial on multi-armed bandits at Simons Institute, Berkeley, CA. Youtube video
    • Aug. 17 Dec. 16, 2022 Co-organizing Fall'22 semester on Data-Driven Decision Processes at Simons Institute, Berkeley, CA
    • June 25-26 Lecturer at IPCO'22 Summer school, Eindhoven, Netherlands
    • May 23-27 Lecturer at CIRM Spring school on theoretical CS devoted to Machine learning, Marseille, France. Youtube video
    • May 5 Invited talk and visit at MIT ORC
    • April 8 (Virtual) Invited talk at CMU Tepper
    • Mar 14-15 "Ask me anything" mentoring workshop at ALT 2022
    2021 [all events are virtual]
    • Oct 24 APS tutorial on "Bandits and Reinforcement Learning" at INFORMS 2021 annual meeting.
    • Sep 15 Seminar at Purdue School of Industrial Engineering.
    • July 19 SNAPP Virtual Seminar . Youtube video
    • July 19-23 Invited talk at 10th World Congress in Probability and Statistics .
    • April 22 Invited talk at IIT Delhi.
    • April 21 Invited talk at Stanford RAIN (Research on Algorithms and Incentives in Networks) seminar.
    • Feb 19 Seminar at Arizona State University, School of Computing and Decision Systems Engineering.
    • Feb 9 Princeton ORFE department seminar.
    2020 [all events are virtual]
    • Dec 4 Invited talk at Illinois Seminar on Data Science and Dynamical Systems, UIUC.
    • Nov 12-14 Invited talk and session at INFORMS 2020 annual meeting.
    • October 27-30 Co-organizing a workhop on Mathematics of Online Decision Making at Simons Institute, Berkeley from Oct 27-30, 2020.
    • Oct 8 Keynote at RL workshop, Amazon Machine Learning Conference.
    • July 17/18 Invited talk at Theory of RL workshop at ICML 2020.
    • July 17/18 Invited talk on "Learning to manage inventory" at Real-World Experiment Design & Active Learning workshop at ICML 2020. Video is here (at 6:01:00))
    • May 18 Our paper on Reinforcement Learning for Integer Programming" won the most popular poster award and honorable mention for the best paper award at MIP 2020.
    • May 2 Online tutorial on Thompson Sampling for reinforcement learning, YSML workshop, Columbia University.

    • December 14, NeurIPS: Speaking at the NeurIPS 2019 Optimization Foundations for Reinforcement Learning Workshop in Vancouver.
    • Nov 18, Caltech: Speaking at Keller Colloquium in Computing and Mathematical Sciences.
    • Nov 8, UT Austin: Speaking at UT Austin McCombs.
    • Oct 30-Nov 1, Columbia: Co-organizing an exciting Symposium on Trustworthy AI at Columbia University.
    • Oct 21, INFORMS: Tutorial on bandits at the INFORMS annual conference in Seattle.
    • Oct 20, INFORMS: Co-chairing Nicholson student paper prize committee with Lewis Ntaimo. Winners to be announced on Oct 20 at INFORMS!
    • Sep-Oct 2019: Serving as Senior PC member for AAAI 2020.
    • Sep 26 2019: Speaking at the Multi Armed Bandit Workshop in London.
    • Sep 23 2019: Speaking at the ARC colloquium at Georgia Tech, Atlanta.