Shipra Agrawal

CYRUS DERMAN ASSOCIATE PROFESSOR OF INDUSTRIAL ENGINEERING AND OPERATIONS RESEARCH

423 S.W. Mudd

Tel(212) 853-0684

Shipra Agrawal’s research spans several  areas of optimization and machine learning, including data-driven optimization under partial, uncertain, and online inputs, and related concepts in learning, namely multi-armed bandits, online learning, and reinforcement learning. She is also interested in prediction markets and game theory. Application areas of her interests include internet advertising, recommendation systems, revenue management, and resource allocation problems. 

Research Interests

Data-driven online decision making, Optimization under uncertainty, Multi-armed bandits, Reinforcement learning, Dynamic pricing and recommendation, Dynamic mechanism design

In the uncertain and dynamic environment of modern businesses, decision makers are often faced with the challenge of making decisions that are not just good or profitable for today, but also put them into better position to face the constraints and uncertainties of tomorrow. In order to achieve this, the decision maker needs to utilize the past observations and data to understand the nature of uncertainties, explore different choices in order to gather useful data for future, and optimize for the long term goals. Agrawal’s research combines optimization and learning techniques to design globally optimal decision-making schemes for such complex, uncertain environments.  Her work is highly interdisciplinary, and lies on the intersection of operations research and data science, spanning the areas of optimization, machine learning, algorithm design, and game theory.

Agrawal received a PhD in Computer Science from Stanford University in June 2011, and was a researcher at Microsoft Research India from July 2011 to August 2015. She is a member of ACM Future of Computing Academy and serves as an associate editor for Management Science journal.

RESEARCH EXPERIENCE

  • Researcher, Microsoft Research (MSR), India, 2013-2015
  • Postdoctoral researcher, Microsoft Research (MSR), India, 2011-2013
  • Member of Research Staff, Bell Labs Alcatel-Lucent, India, Dec 2004-Aug 2006

PROFESSIONAL EXPERIENCE

  • Software Engineer, Yahoo! Software India Pvt. Ltd., India, Aug 2004-Dec 2004

PROFESSIONAL AFFILIATIONS

  • Member of ACM Future of Computing Academy
  • Associate editor for Management Science journal

HONORS & AWARDS

  • Selected as an inaugural member of the ACM Future of Computing Academy (FCA). Announced April 2017.
  • Provosts Grant for Junior Faculty who Contribute to the Diversity Goals of the University (2016-2017)

SELECTED PUBLICATIONS

  • A complete updated list is available at http://www.columbia.edu/~sa3305/
  • S. Agrawal, N. Goyal, "Near-optimal regret bounds for Thompson Sampling" Forthcoming in the Journal of ACM (2017).
  • S. Agrawal, V. Avandhanula, V. Goyal, A. Zeevi, "Thompson Sampling for MNL-bandit". Conference on Learning Theory (COLT), 2017.
  • S. Agrawal, V. Avandhanula, V. Goyal, A. Zeevi, "An Exploration-Exploitation Approach for Assortment Selection". ACM conference on Economics and Computation (EC) 2016.
  • S. Agrawal, N. R. Devanur, "Fast algorithms for online stochastic convex programming". In Proceedings of the 21st Annual ACM-SIAM Symposium on Discrete Algorithms (SODA), 2015.
  • S. Agrawal, N. R. Devanur, "Bandits with concave rewards and convex knapsacks". In Proceedings of the 15th ACM Conference on Electronic Commerce (EC), 2014. 
  • S. Agrawal, Z. Wang and Y. Ye, "A Dynamic Near-Optimal Algorithm for Online Linear Programming". Operations Research 62:876-890 (2014).
  • S. Agrawal, N. Goyal, "Thompson Sampling for contextual bandits with linear payoffs". In Proceedings of the 30th International Conference on Machine Learning (ICML), 2013. 
  • S. Agrawal, N. Goyal, "Analysis of Thompson Sampling for the multi-armed bandit problem". In Proceedings of the 25th Annual Conference on Learning Theory (COLT), 2012.
  • S. Agrawal, Y. Ding, A. Saberi, and Y. Ye, "Price of Correlations in Stochastic Optimization". Operations Research 60:243-248 (2012).
  • S. Agrawal, E. Delage, M. Peters, Z. Wang, and Y. Ye, "A Unified Framework for Dynamic Prediction Market Design". Operations Research 59:3:550-568 (2011).