Publications

Working Papers

• Socially Fair Reinforcement Learning
  Debmalya Mandal, Jiarui Gan
  [Paper]

• Corruption Robust Reinforcement Learning with Human Feedback
Debmalya Mandal, Andi Nika, Parameswaran Kamalaruban, Adish Singla, and Goran Radanovic
[Paper]

Accepted Papers

• The Effectiveness of Surprisingly Popular Voting with Partial Preferences
Hadi Hosseini, Debmalya Mandal, and Amrit Puhan
In the 38th Annual Conference on Neural Information Processing Systems (NeurIPS-2024)
[ArXiv]

• Symmetric Linear Bandits with Hidden Symmetry
Nam Tran, The-Anh Ta, Debmalya Mandal, and Long Tran-Thanh
In the 38th Annual Conference on Neural Information Processing Systems (NeurIPS-2024)
[ArXiv]

• Learning the Expected Core of Strictly Convex Stochastic Cooperative Games
Nam Tran, The-Anh Ta, Shuqing Shi, Debmalya Mandal, Long Tran-Thanh, and Yali Du
In the 38th Annual Conference on Neural Information Processing Systems (NeurIPS-2024)
[ArXiv]

• Agent Specific Effects: A Causal Effect Propagation Analysis in Multi-Agent MDPs
Stelios Triantafyllou, Aleksa Sukovic, Debmalya Mandal, and Goran Radanovic
In the 41st International Conference on Machine Learning (ICML-2024)
[ArXiv]

• Reward Model Learning vs. Direct Policy Optimization: A Comparative Analysis of Learning from Human Preferences
Andi Nika, Debmalya Mandal, Parameswaran Kamalaruban, George Tzannetos, Goran Radanovic, and Adish Singla
In the 41st International Conference on Machine Learning (ICML-2024)
[ArXiv]

• Performative Reinforcement Learning in Gradually Shifting Environments
  Ben Rank, Stelios Triantafyllou, Debmalya Mandal, and Goran Radanovic
  In the 40th Conference on Uncertainty in Artificial Intelligence (UAI-2024)
  [ArXiv]

• Corruption-Robust Offline Two-Player Zero-Sum Markov Games
  Andi Nika, Debmalya Mandal, Adish Singla, and Goran Radanovic
  In the 27th International Conference on Artificial Intelligence and Statistics (AIStats-2024)
  [ArXiv]

• Sequential Principal-Agent Problems with Communication: Efficient Computation and Learning
  Jiarui Gan, Rupak Majumdar, Debmalya Mandal, and Goran Radanovic
  In the 23rd International Conference on Autonomous Agents and Multiagent Systems (AAMAS-2024)
  Extended Abstract
  [ArXiv]

• Performative Reinforcement Learning
  Debmalya Mandal, Stelios Triantafyllou, and Goran Radanovic
  In the 40th International Conference on Machine Learning (ICML-2023)
  [Paper]

• Implicit Poisoning Attacks in Two-Agent Reinforcement Learning: Adversarial Policies for Training-Time Attacks
  Mohammad Mohammadi, Jonathan Nöther, Debmalya Mandal, Adish Singla, and Goran Radanovic
  In the 22nd International Conference on Autonomous Agents and Multiagent Systems (AAMAS-2023)
  [Link]

• Representation-Based Individual Fairness in k-Clustering
  Debjyoti Kar, Mert Kosan, Debmalya Mandal, Sourav Medya, Arlei Silva, Palash Dey, and Swagato Sanyal
  In the 22nd International Conference on Autonomous Agents and Multiagent Systems (AAMAS-2023)
  Extended Abstract
  [Paper]

• Online Reinforcement Learning with Uncertain Episode Lengths
  Debmalya Mandal, Goran Radanovic, Jiarui Gan, Adish Singla, and Rupak Majumdar
  In the 37th AAAI Conference on Artificial Intelligence (AAAI-2023)
  Oral Presentation
  [Link]

• Markov Decision Processes with Time-Varying Geometric Discounting
  Jiarui Gan, Annika Hennes, Rupak Majumdar, Debmalya Mandal, and Goran Radanovic
  In the 37th AAAI Conference on Artificial Intelligence (AAAI-2023)
  Oral Presentation
  [Paper]

• Learning Tensor Representations for Meta-Learning
  Samuel Deng, Yilin Guo, Daniel Hsu, and Debmalya Mandal
  In the 25th International Conference on Artificial Intelligence and Statistics (AISTATS-2022)
  [Paper]

• Sequential Blocked Matching
  Nick Bishop, Hau Chan, Debmalya Mandal, and Long Tran-Thanh
  In the 36th AAAI Conference on Artificial Intelligence (AAAI-2022)
  [Paper]

• Meta-Learning with Graph Neural Networks: Methods and Applications
  Debmalya Mandal, Sourav Medya, Brian Uzzi, and Charu Aggarwal
  In the ACM SIGKDD Explorations Newsletter (SIGKDD Explorations-2021)
  [Paper]

• Surprisingly Popular Voting Recovers Rankings, Surprisingly!
  Hadi Hosseini, Debmalya Mandal, Nisarg Shah, and Kevin Shi
  In the Proc. of 30th International Joint Conference on Artificial Intelligence (IJCAI-2021)
  [Paper | Data | ACM Tech News]
• Ensuring Fairness Beyond the Training Data
  Debmalya Mandal, Samuel Deng, Suman Jana, Jeannette M. Wing, and Daniel Hsu
  In the 34th Conference on Neural Information Processing Systems (NeurIPS-2020)
  [NeurIPS Paper | Code]
• Adversarial Blocking Bandits
  Nick Bishop, Hau Chan, Debmalya Mandal, and Long Tran-Thanh
  In the 34th Conference on Neural Information Processing Systems (NeurIPS-2020)
  [NeurIPS Paper]
• Peer Prediction with Heterogeneous Users
  Arpit Agarwal, Debmalya Mandal, David C. Parkes, and Nisarg Shah
  In the Transaction on Economics and Computation (TEAC-2020)
  Supersedes the EC-2017 paper below
  [TEAC Paper]
• Optimal Communication-Distortion Tradeoff in Voting
  Debmalya Mandal, Nisarg Shah, and David P. Woodruff
  In the Twenty-First ACM Conference on Economics and Computation (EC-2020)
  [EC Paper | Full Version]
• The Effectiveness of Peer Prediction in Long-Term Forecasting
  Debmalya Mandal, Goran Radanovic, and David C. Parkes
  In the 34th AAAI Conference on Artificial Intelligence (AAAI-2020)
  Spotlight Presentation
  [AAAI Paper | data]
• Efficient and Thrifty Voting by Any Means Necessary
  Debmalya Mandal, Ariel D. Procaccia, Nisarg Shah, and David P. Woodruff
  In the 33rd Conference on Neural Information Processing Systems (NeurIPS-2019)
  Oral Presentation (One of 36 Out of 1428 Accepted Papers)
  [NeurIPS Paper | Slides]
• Weighted Tensor Completion for Time-Series Causal Inference
  Debmalya Mandal, and David C. Parkes
  In the NeurIPS Workshop on Causal Learning (CausalML-2018)
  [Paper]
• Peer Prediction with Heterogeneous Users
  Arpit Agarwal, Debmalya Mandal, David C. Parkes, and Nisarg Shah
  In the 18th ACM Conference on Economics and Computation (EC-2017)
  Invited for the Special Issue on Selected Papers from EC-2017
  [EC Paper]
• Calibrated Fairness in Bandits
  Yang Liu, Goran Radanovic, Christos Dimitrakakis, Debmalya Mandal, and David C. Parkes
  In the Fourth Workshop on Fairness, Accountability, and Transparency in Machine Learning (FAT/ML-2017)
  [FATML Paper]
• Peer Prediction with Heterogeneous Tasks
  Debmalya Mandal, Matthew Leifer, David C. Parkes, Galen Pickard, and Victor Shnayder
  In NIPS Workshop on Crowdsourcing and Machine Learning (CrowdML-2016)
  [CrowdML Paper]
• Correlated Voting
  Debmalya Mandal, and David C. Parkes
  In the 25th International Joint Conference on Artificial Intelligence (IJCAI-2016)
  [IJCAI Paper]
• A Stackelberg Game Approach for Incentivizing Participation in Online Educational Forums with Heterogeneous Student Population
  Rohith D. Vallam, Priyanka Bhatt, Debmalya Mandal, and Yadati Narahari
  In the 29th AAAI Conference on Artificial Intelligence (AAAI-2015)
  [AAAI Paper]
• Novel Mechanisms for Online Crowdsourcing with Unreliable, Strategic Agents
  Praphul Chandra, Yadati Narahari, Debmalya Mandal, and Prasenjit Dey
  In the 29th AAAI Conference on Artificial Intelligence (AAAI-2015)
  [AAAI Paper]
• A Truthful Budget Feasible Multi-Armed Bandit Mechanism for Crowdsourcing Time Critical Tasks
  Arpita Biswas, Shweta Jain, Debmalya Mandal, and Yadati Narahari
  In the 14th International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS-2015)
  [AAMAS Paper]
• Profit Maximizing Prior-free Multi-unit Procurement Auctions with Capacitated Sellers
  Arupratan Ray, Debmalya Mandal, and Yadati Narahari
  In the 14th International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS-2015)
  Extended Abstract
  [AAMAS Paper]
• A Novel Ex-Post Truthful Mechanism for Multi-Slot Sponsored Search Auctions
  Debmalya Mandal, and Yadati Narahari
  In the 13th International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS-2014)
  Extended Abstract
  [AAMAS Paper]