Research

Broadly, I am interested in optimization and learning in the context of economics and computer science. Specifically, my interests include first-order methods, online learning, equlibrium computation, as well as fairness and privacy issues in game-theoretic settings.

Publications

Conference Papers

  • D. Chakrabarti, J. Grand-Clément, C. Kroer (2024). Extensive-Form Game Solving via Blackwell Approachability on Treeplexes. Neural Information Processing Systems (NeurIPS). Spotlight Paper.
  • J. Černý, C. K. Ling, D. Chakrabarti, J. Zhang, G. Farina, C. Kroer, G. Iyengar (2024). Contested Logistics: A Game-Theoretic Approach. Conference on Game Theory and AI for Security (GameSec). Best Paper.
  • D. Chakrabarti, G. Farina, C. Kroer (2024). Efficient Online Learning on Polytopes with Linear Minimization Oracles. Conference on Artificial Intelligence (AAAI).
  • M. Curry, V. Thoma, D. Chakrabarti, S.M. McAleer, C. Kroer, T. Sandholm, N. He, S. Seuken (2024). Automated Design of Affine Maximizer Mechanisms in Dynamic Settings. Conference on Artificial Intelligence (AAAI).
  • S.A. Esmaeili, D. Chakrabarti, H. Grape, B. Brubach (2024). Implications of Distance over Redistricting Maps: Central and Outlier Maps. Conference on Artificial Intelligence (AAAI).
  • D. Chakrabarti, J. Diakonikolas, C. Kroer (2023). Block-Coordinate Methods and Restarting for Solving Extensive-Form Games. Neural Information Processing Systems (NeurIPS).
  • D. Chakrabarti, J.P. Dickerson, S.A. Esmaeili, A. Srinivasan, and L. Tsepenekas (2022). A New Notion of Individually Fair Clustering: α-Equitable k-Center International Conference on Artificial Intelligence and Statistics (AISTATS).
  • D. Chakrabarti, J. Gao, A. Saraf, G. Schoenebeck, and F. Yu (2022). Optimal Local Bayesian Differential Privacy over Markov Chains (Extended Abstract). International Conference on Autonomous Agents and Multiagent Systems (AAMAS).
  • B. Brubach, D. Chakrabarti, J.P. Dickerson, A. Srinivasan, and L. Tsepenekas (2021). A General Framework for Clustering with Stochastic Pairwise Constraints. Conference on Artificial Intelligence (AAAI).
  • B. Brubach, D. Chakrabarti, J.P. Dickerson, S. Khuller, A. Srinivasan, and L. Tsepenekas (2020). A Pairwise Fair and Community-preserving Approach to k-Center Clustering. International Conference on Machine Learning (ICML).

Refereed Workshop Papers

  • D. Chakrabarti, G. Farina, C. Kroer (2023). Efficient Learning in Polyhedral Games via Best Response Oracles. NeurIPS 2023 Workshop on Optimization for Machine Learning (OPT 2023).
  • M. Curry, V. Thoma, D. Chakrabarti, S.M. McAleer, C. Kroer, T. Sandholm, N. He, S. Seuken (2023). Automated Design of Affine Maximizer Mechanisms in Dynamic Settings. European Workshops on Reinforcement Learning (EWRL16).
  • G. Brero, D. Chakrabarti, A. Eden, M. Gerstgrasser, V. Li, and D. Parkes (2021). Learning Stackelberg Equilibria in Sequential Price Mechanisms. ICML 2021 Workshop on Reinforcement Learning Theory.
  • D. Chakrabarti, J. Gao, A. Saraf, G. Schoenebeck, and F. Yu (2020). Optimal Local Bayesian Differential Privacy over Markov Chains. Mechanism Design for Social Good (MD4SG).