S. Agrawal, V. Avandhanula, V. Goyal, A. Zeevi, "MNL-Bandit: A Dynamic Learning Approach to Assortment Selection". Accepted for publication in Operations Research Journal.

S. Agrawal, N. R. Devanur, "Bandits with global convex constraints and objective". Accepted for publication in Operations Research Journal.

S. Agrawal, N. Goyal, "Near-optimal regret bounds for Thompson Sampling", Journal of the ACM (JACM), Volume 64 Issue 5, October 2017. [ pdf ] [ EE ].

T. Kocak, M. Valko, R. Munos, S. Agrawal, "Spectral Bandits for Smooth Graph Functions". Forthcoming in Journal of Machine Learning Research.

S. Agrawal, Z. Wang and Y. Ye, "A Dynamic Near-Optimal Algorithm for Online Linear Programming". Operations Research 62:876-890 (2014). [ EE ] [ arXiv ]

S. Agrawal, Y. Ding, A. Saberi, and Y. Ye, "Price of Correlations in Stochastic Optimization". Operations Research 60:243-248 (2012). [ EE ]

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). [ EE ] [ arXiv ]

S. Agrawal, N. Megiddo and B. Armbruster, "Equilibrium in Prediction Markets with Buyers and Sellers". Economic Letters 109:46-49 (2010). [ EE ] [ pdf ]

S. Agrawal, J.R. Haritsa and B.A. Prakash, "FRAPP: A Framework for High-Accuracy Privacy-Preserving Mining". Data Mining and Knowledge Discovery Journal 18:101-139 (2009). [ EE ] [ arXiv ]

S. Agrawal, C. N. Kanthi, K. V. M. Naidu, J. Ramamirtham, R. Rastogi, S. Satkin, and A. Srinivasan, Monitoring infrastructure for converged networks and services". Bell Labs Technical Journal 12(2): 63-77 (2007). [ EE ]

Reinforcement Learning for Integer Programming: Learning to Cut, Yunhao Tang, Shipra Agrawal, Yuri Faenza. Working paper. [arXiv]

S. Agrawal and R. Jia, Learning in structured MDPs with convex cost functions: Improved regret bounds for inventory management. ACM conference on Eoconomics and Computation (EC) 2019. [arXiv]

S. Agrawal, M. Shadravan, C. Stein, Submodular Secretary Problem with Shortlists, ITCS (Innovations in Theoretical Computer Science) 2019. [ arXiv ]

S. Agrawal, V. Mirrokni, M. Zadimoghaddam, Proportional Allocation: Simple, Distributed, and Diverse Matching with High Entropy, ICML 2018. [ pdf ]

C. Pike-Burke, S. Agrawal, S. Grunewalder, C. Szepesvari, Bandits with Delayed, Aggregated Anonymous Feedback, ICML 2018. [ arXiv ][ICML]

S. Agrawal, C. Daskalakis, V. Mirrokni, B. Sivan, Robust Repeated Auctions under Heterogeneous Buyer Behavior, EC 2018. [ arXiv ]

Y. Tang, S. Agrawal, Exploration by Distributional Reinforcement Learning, IJCAI 2018. [ arXiv ]

S. Agrawal and R. Jia, "Optimistic posterior sampling for reinforcement learning: worst-case regret bounds". NIPS 2017 (spotlight) [ arXiv ]

S. Agrawal, V. Avandhanula, V. Goyal, A. Zeevi, "Thompson Sampling for MNL-bandit". Conference on Learning Theory (COLT), 2017. [ arXiv ]

S. Agrawal, N. R. Devanur, "Linear Contextual Bandits with Knapsacks". NIPS 2016. [EE][ arXiv ]

S. Agrawal, V. Avandhanula, V. Goyal, A. Zeevi, "An Exploration-Exploitation Approach for Assortment Selection". ACM conference on Eoconomics and Computation (EC) 2016. [ EE ][ pdf ]

S. Agrawal, N. R. Devanur, L. Li, "An efficient algorithm for contextual bandits with knapsacks, and an extension to concave objectives". Conference on Learning Theory (COLT) 2016. [EE][arXiv ]

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. [ EE ] [ arXiv ]

S. Agrawal, N. R. Devanur, "Bandits with concave rewards and convex knapsacks". In Proceedings of the 15th ACM Conference on Electronic Commerce (EC), 2014. [ EE ] [ arXiv ]

T. Kocak, M. Valko and R. Munos, S. Agrawal, "Spectral Thompson Sampling". In Proceedings of the 28th AAAI Conference on Artificial Intelligence (AAAI), 2014. [ pdf ]

S. Agrawal, N. Goyal, "Thompson Sampling for contextual bandits with linear payoffs". In Proceedings of the 30th International Conference on Machine Learning (ICML), 2013. [ pdf ] [ arXiv ]

S. Agrawal, N. Goyal, "Further optimal regret bounds for Thompson Sampling", In Proceedings of the 16th International Conference on Artificial Intelligence and Statistics (AISTATS), 2013. [ pdf ] [ arXiv ]

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. [ pdf ] [ arXiv ]

"Correlation Robust Stochastic Optimization". In Proceedings of the Twenty-First Annual ACM-SIAM Symposium on Discrete Algorithms (SODA), 2010. [ EE ] [ arXiv ]

"A Unified Framework for Dynamic Parimutuel Information Market Design". In Proceedings of the 10th ACM Conference on Electronic Commerce (EC), 2009. [ EE ]

S. Agrawal, Z. Wang and Y. Ye, "Parimutuel Betting on Permutations". In Proceedings of the 4th International Workshop On Internet And Network Economics (WINE), 2008. [ EE ] [ arXiv ]

S. Agrawal, K.V.M. Naidu and R. Rastogi, "Diagnosing Link-Level Anomalies Using Passive Probes". In Proceedings of the 26th Annual IEEE Conference on Computer Communications (INFOCOM), 2007. [ EE ]

S. Agrawal, S. Deb, K.V.M. Naidu, and R. Rastogi, Efficient Detection of Distributed Constraint Violations". Short paper. In Proceedings of the 23rd International Conference on Data Engineering (ICDE), 2007. [ EE ]

S. Agrawal, P.P.S. Narayan, J. Ramamirtham, R. Rastogi, M. Smith, K. Swanson, and M. Thottan, "VoIP service quality monitoring using active and passive probes" . In Proceedings of the First International Conference on COM- munication System softWAre and MiddlewaRE (COMSWARE), 2006. [ EE ]

S. Agrawal, J.R. Haritsa, "A Framework for High-Accuracy Privacy-Preserving Mining". In Proceedings of the 21st International Conference on Data Engineering (ICDE), 2005. [ EE ] [ arXiv ]

S. Agrawal, V. Krishnan and J.R. Haritsa, On Addressing Efficiency Concerns in Privacy-Preserving Mining". In Proceedings of the 9th International Conference on Database Systems for Advanced Applications (DASFAA), 2004. [ EE ] [ arXiv ]