Research

Journal Publications

• Online Resource Allocation with Convex-set Machine-Learned Advice, Operations Research, forthcoming.
  • with P. Jaillet and Zijie Zhou
• Multi-channel Autobidding with Budget and ROI Constraints, Management Science, forthcoming.
  • with Y. Deng, P. Jaillet, J. Liang, V. Mirrokni.
• Learning to Adapt in Non-Stationary Bandits with Autoregressive Temporal Structure, Mathematics of Operations Research, accepted, 2026.
  • with Q. Chen and D. Bouneffouf
• Technical Note—Active Learning for Nonparametric Choice Models, Operations Research, 74(2), 730–751, 2026.
  • with F. Susan, E. Emamjomeh-Zadeh, D. Kempe
  • Honorable Mention, INFORMS Minority Issues Forum Student Poster Competition, entrant: F. Susan, 2022.
• Upfront Commitment in Online Resource Allocation with Patient Customers, Management Science, 72(5), 4087–4105, 2026.
  • with E. Yao
  • An earlier title: Online Resource Allocation with Time-Flexible Customers
• Learning in Repeated Multi-Unit Pay-As-Bid Auctions, Manufacturing & Service Operations Management, 27(1), 2025.
  • with R. Galgana
• Optimal Learning for Structured Bandits, Management Science, Volume 70, Issue 6, pp. 3951–3998, 2024 | Presentation Video @Rensselaer Polytechnic Institute
  • with B. Van Parys
• Online Learning via Offline Greedy Algorithms: Applications in Market Design and Optimization, Management Science, Volume 69, Issue 7, pp. 3797–3817, 2023| Presentation Video @Simons Institute
  • with R. Niazadeh, J. Wang, F. Susan, A. Badanidiyuru
  • The 2021 Data Mining Paper Competition (General Track, finalist)
• Contextual Bandits with Cross-learning, Mathematics of Operations Research, Volume 48, Issue 3, 2023
  • with S. Balseiro, M. Mahdian, V. Mirrokni, J. Schneider
• Linear Program based Approximation of Personalized Reserve Prices, Management Science, Volume 68, Issue 3, pp. 1849-1864, 2022
  • with M. Derakhshan, R. Paes Leme,
  • An earlier version of this paper was entitled “Data-driven Optimization of Personalized Reserve Prices.”
• Learning Product Rankings Robust to Fake Users, Operations Research, Volume 71, Issue 4, pp. 1171–1196, 2023 |Presentation Video by S. Sekar @ EC 2021
  • with V. Manshadi, J. Schneider, S. Sekar
  • Best OM Paper Award from Operations Research journal (2025)
  • The 2023 INFORMS Minority Issues Forum (MIF) award (winner)
  • The 2022 INFORMS Data Mining Best Paper Competition (General Track, finalist)
• Improved Approximations for Free-Order Prophets and Second-Price Auctions, Operations Research, 69(6), 1805–1822, 2021.
  • with H. Beyhaghi, R. Paes Leme, M. Pal, and B. Sivan,
• Dynamic Incentive-Aware Learning: Robust Pricing in Contextual Auctions, Operations Research, Volume 69, Issue 1, pp. 297–314, 2021 | Presentation video @MIT Operations Research Center
  • with A. Javanmard, V. Mirrokni
• Product Ranking on Online Platforms, Management Science Volume 68, Issue 6, pp. 4024–4041, 2022| Presentation video @EC 2020
  • with M. Derakhshan, V. Manshadi, V. Mirrokni
  • Accepted for presentation at the MSOM Service SIG, 2018.
  • An earlier version of this paper was entitled “Two-stage Pandora’s Box for Product Ranking.”
• Dynamic Pricing for Heterogeneous Time-Sensitive Customers, Manufacturing & Service Operations Management, Volume 22, Issue 3, pp. 562–581, 2020.
  • with H. Nazerzadeh, R. Randhawa
  • The 2019 Service Science Best Paper Award (finalist)
• Auctions with Dynamic Costly Information Acquisition, Operations Research, Volume 65, Issue 1, pp. 130 - 144, 2016.
  • with H. Nazerzadeh
• Real-time Optimization of Personalized Assortments, Management Science, Volume 60, Issue 6, pp. 1532 - 1551, 2014.
  • with H. Nazerzadeh, P. Rusmevichientong
  • The 2016 MSOM Student Paper Competition (finalist)
  • The 2017 POMS Supply Chain Management College Student Paper Competition (finalist)

Working Papers

• Market Design for Generative AI: Beyond the Copyright Binary, working paper, 2026. Earlier title: “Market Design for AI: Beyond the Copyright Binary.” Accepted for presentation at the 2026 M&SOM Service Operations SIG.
  • with Y. Dai, M. Farboodi, S. Shahshahani
• Policy Regret for Embedding Model Routing: Contextual Bandits with Low-Rank Experts, working paper, 2026.
  • with Y. Dai, P. Jaillet
• Efficiency, Feasibility, and Incentive-Awareness in Constrained Online Resource Allocation, under review at Operations Research. Earlier conference version: NeurIPS 2025.
  • with Y. Dai, P. Jaillet
• Robust Multi-Item Demand Autobidding Auctions, under review at Management Science, 2026.
  • with R. Galgana, Y. Teng
• Gap-Based Learning in Multi-Unit Markets, under review at Operations Research, 2026. Earlier SSRN title: “Gap Based Learning in Markets.”
  • with R. Galgana
• Nash Equilibria in Uniform Price Auctions: Theory, Computation, and Market Insights, major revision at Manufacturing & Service Operations Management.
  • with Y. Feng, Q. Li
• Fair Assortment Planning, Operations Research, Minor Revision.
  • with Q. Chen, F. Susan
  • The 2022 INFORMS Social Media Analytics Best Student Paper Competition (entrant: Q. Chen, finalist)
  • The 2022 INFORMS IBM Best Student Paper Award Competition (entrant: Q. Chen, finalist)
  • Accepted for presentation at the 2022 MSOM Service SIG
  • Spotlight Presentation at the 2022 Revenue Management & Pricing Conference
  • Honorable Mention, INFORMS Minority Issues Forum Student Poster Competition, entrant: Q. Chen, 2022.
• Learning Safe Strategies for Value Maximizing Buyers in Uniform Price Auctions, Management Science, Major Revision.
  • with S. Sahoo.
  • The 2025 INFORMS Jeff McGill Student Paper Award (entrant: S. Sahoo, First Place)
  • The 2025 INFORMS Rothkopf Best Student Paper Award Competition (entrant: S. Sahoo, Second Place)
• Online Resource Allocation with Samples, Operations Research, Major Revision.
  • with P. Jaillet and Zijie Zhou

Selected Refereed Conference Papers

• Safe Strategies in Multi-Unit Auctions: Equilibria, Liquid Welfare, and Revenue, Web and Internet Economics (WINE), 2026.
  • with S. Sahoo
• Optimal Contest beyond Convexity, Annual ACM Symposium on Theory of Computing (STOC), 2026
  • with M. Hajiaghayi and S. Shin
• Learning to bid in discriminatory auctions with budget constraints, Conference on Artificial Intelligence and Statistics (AISTATS), 2026.
  • with S. Sahoo
  • Accepted for a Spotlight presentation
• Nash Equilibria in Uniform Price Auctions: Theory, Computation, and Market Insights, ACM SIGMETRICS 2026
  • with Y. Feng and Q. Li.
• Incentive-Aware Dynamic Resource Allocation under Long-Term Cost Constraints, The Proceedings of the Conference on Neural Information Processing Systems (NeurIPS), 2025.
  • with Y. Dai and P. Jaillet.
  • 1st Place in the ACM Student Research Competition (SRC) at SIGMETRICS 2025 (entrant: Y. Dai)
• Learning Safe Strategies for Value Maximizing Buyers in Uniform Price Auctions, The International Conference on Machine Learning (ICML), July 13 - 19, 2025.
  • with S. Sahoo.
  • The 2025 INFORMS Jeff McGill Student Paper Award (entrant: S. Sahoo, First Place)
  • The 2025 INFORMS Rothkopf Best Student Paper Award Competition (entrant: S. Sahoo, Second Place)
• Interpolating Item and User Fairness in Recommendation Systems, The Proceedings of the Conference on Neural Information Processing Systems (NeurIPS), 2024.
  • with Q. Chen, J. Liang, and D. Bouneffouf
  • Preliminary version was accepted at the 5th Annual Symposium on Foundations of Responsible Computing (FORC), 2024.
• Online Combinatorial Optimization with Group Fairness Constraints, International Joint Conferences on Artificial Intelligence (IJCAI), 2024.
  • with R. Niazadeh, K. Patel, F. Susan
  • Distinguished Paper Award recognizing three of the best papers presented at IJCAI
• Individual Welfare Guarantees in the Autobidding World with Machine-learned Advice, Web Conference (WWW), May 13-17, 2024.
  • with Y. Deng, P. Jaillet, J. Liang, V. Mirrokni
• Non-Stationary Bandits with Auto-Regressive Temporal Dependency, The Proceedings of the Conference on Neural Information Processing Systems (NeurIPS), 2023.
  • with Q. Chen, D. Bouneffouf
  • Earlier titles: “Dynamic Bandits with Temporal Structure” and “Dynamic Bandits with an Auto-Regressive Temporal Structure”
• Learning and Collusion in Multi-unit Auctions, The Proceedings of the Conference on Neural Information Processing Systems (NeurIPS), 2023.
  • with S. Brânzei, M. Derakhshan, and Y. Han
• Multi-channel Autobidding with Budget and ROI Constraints, The International Conference on Machine Learning (ICML), July 25 - 27, 2023.
  • with Y. Deng, P. Jaillet, J. Liang, V. Mirrokni.
• Pricing against a Budget and ROI Constrained Buyer, Conference on Artificial Intelligence and Statistics (AISTATS), Apr. 25 - Apr. 27, 2023.
  • with P. Jaillet, J. Liang, V. Mirrokni,
• Incentive-aware Contextual Pricing with Non-parametric Market Noise, Conference on Artificial Intelligence and Statistics (AISTATS), Apr. 25 - Apr. 27, 2023.
  • with P. Jaillet, J. Liang
• Online Learning via Offline Greedy Algorithms: Applications in Market Design and Optimization, The Proceedings of the 22nd ACM Conference on Economics and Computation (EC), pp. 737-738, July 20-22, 2021.| Presentation Video @Simons Institute
  • with R. Niazadeh, J. Wang, F. Susan, A. Badanidiyuru
  • The 2021 Data Mining Paper Competition (General Track, finalist)
• Learning Product Rankings Robust to Fake Users, The Proceedings of the 22nd ACM Conference on Economics and Computation (EC), pp. 560-561, July 20-22, 2021. | Presentation Video @ C3 Digital Transformation Institute
  • with V. Manshadi, J. Schneider, S. Sekar
  • The 2022 INFORMS Data Mining Best Paper Competition (General Track, finalist)
  • The 2023 INFORMS Minority Issues Forum (MIF) award (winner)
• Boosted Second Price Auctions: Revenue Optimization for Heterogeneous Bidders, The ACM Special Interest Group on Knowledge Discovery and Data Mining (SIGKDD Conference), pp. 447-457, Aug. 23-27, 2021.
  • with M. Lin, V. Mirrokni, H. Nazerzadeh
  • The 2018 INFORMS Data Mining Paper Competition (finalist)
• Auction Design for ROI-Constrained Buyers, Web Conference (WWW), pp. 3941-3952, Apr.19-23, 2021. | Presentation video @2021 Web Conference
  • with I. Lobel, R. Paes Leme
• No-regret Learning in Price Competitions under Consumer Reference Effects, The Proceedings of the Conference on Neural Information Processing Systems (NeurIPS), pp. 21416-21427, Dec. 6-12, 2020.
  • with P. Jaillet, J. Liang
• Product Ranking on Online Platforms, The Proceedings of the 21st ACM Conference on Economics and Computation (EC), pp. 459-459, July 13-17, 2020. | Presentation video @EC 2020
  • with M. Derakhshan, V. Manshadi, V. Mirrokni
• LP-based Approximation of Personalized Reserve Prices, The Proceedings of the 20th ACM Conference on Economics and Computation (EC), pp. 589-589, June 24-28, 2019.
  • with M. Derakhshan, R. Paes Leme
• Contextual Bandits with Cross-learning, The Proceedings of the Conference on Neural Information Processing Systems (NeurIPS), pp. 9676 - 9685, Vancouver, Canada, Dec. 8-14, 2019.
  • with S. Balseiro, M. Mahdian, V. Mirrokni, J. Schneider
• Dynamic Incentive-Aware Learning: Robust Pricing in Contextual Auctions, The Proceedings of the Conference on Neural Information Processing Systems (NeurIPS), pp. 9756 – 9766, Vancouver, Canada, Dec. 8-14, 2019. | Presentation video @MIT Operations Research Center
  • with A. Javanmard, V. Mirrokni
  • An earlier version of this paper accepted to NeurIPS 2019.
• Real-time Optimization of Personalized Assortments, 14th ACM Conference on Electronic Commerce (EC), pp. 561 - 562, Philadelphia, PA, June 16-20, 2013.
  • with H. Nazerzadeh, P. Rusmevichientong
  • The 2016 MSOM Student Paper Competition (finalist)
  • The 2017 POMS Supply Chain Management College Student Paper Competition (finalist)

Workshops and Symposia

• MACS: A Hybrid Multi-Agent Framework for Reliable Conversational E-Commerce Recommendation, NeurIPS Workshop “Who Verifies the Agents?”, 2026. Workshop version: “MACS: Verifying Persistent Constraint Compliance in Multi-Turn LLM Agents.”
  • with J. Huang, H. Clay, S. Beygi, T. Sarda, A. Saberi
• The Risks and Rewards of User Expressiveness in Revenue-Driven Recommendation, NeurIPS MLxOR Workshop, 2026.
  • with Y. Alimohammadi and R. Galgana
• Entropy Guided Diversification and Preference Elicitation in Agentic Recommendation Systems, Proceedings of the AAAI Symposium Series, 8(1), 2026.
  • with D. Tran, Y. Li, H. Clay, S. Beygi, A. Saberi

Ph.D. Thesis

• Efficient Policies and Mechanisms for Online Platforms
  • George B. Dantzig Dissertation Award (2017)
  • INFORMS Revenue Management and Pricing Section Dissertation Prize (2017)
  • Elwood S. Buffa Doctoral Dissertation Award (2018)
  • University of Southern California (USC) Ph.D. Achievement Award (2017)

Journal Publications in Wireless Communications

• Scaling Behaviors of Wireless Device-to-Device Communications with Distributed Caching, IEEE Transactions on Information Theory, Volume 60, Issue 7, pp. 4286 - 4298, 2014
  • with A.G. Dimakis, A.F. Molisch
• Base-Station Assisted Device-to-Device Communications for High-Throughput Wireless Video Networks, IEEE Transactions on Wireless Communications, Volume 13, Issue 7, pp. 3665 - 3676, 2014.
  • with P. Mansourifard, A.F. Molisch, A.G. Dimakis
• FemtoCaching: Wireless Video Content Delivery through Distributed Caching Helpers, IEEE Transactions on Information Theory, Volume 59, Issue 12, pp. 8402 - 8413, 2013
  • with K. Shanmugam, A.G. Dimakis, A.F. Molisch, G. Caire
• Device-to-Device Collaboration: A New Architecture for Wireless Video Distribution, IEEE Communications Magazine, Volume 51, Issue 4, pp. 142 - 149, 2013
  • with A.F. Molisch, A.G. Dimakis, G. Caire