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.
T. Kocak, M. Valko, R. Munos, S. Agrawal, "Spectral Bandits for Smooth Graph Functions". Forthcoming in Journal of Machine Learning Research.
S. Agrawal, Y. Ding, A. Saberi, and Y. Ye, "Price of Correlations in Stochastic Optimization". Operations Research 60:243-248 (2012). [ EE ]
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 ]
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 ]
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, "Further optimal regret bounds for Thompson Sampling", In Proceedings of the 16th International Conference on Artificial Intelligence and Statistics (AISTATS), 2013. [ pdf ] [ 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, 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, 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 ]