("α-β" denotes alphabetical ordering)
Distortion of AI Alignment: Does Preference Optimization Optimize for Preferences?
(α-β) Paul Gölz, Nika Haghtalab, Kunhe Yang
To appear at the 39th Annual Conference on Neural Information Processing Systems (NeurIPS 2025)
Presented at the 2nd Workshop on New Directions in Social Choice at EC 2025 (oral)
[arXiv]
Leakage-Robust Bayesian Persuasion
(α-β) Nika Haghtalab, Mingda Qiao, Kunhe Yang
In Proceedings of the 26th ACM Conference on Economics and Computation (EC 2025)
[arXiv] [EC extended abstract]
Should Decision-Makers Reveal Classifiers in Online Strategic Classification?
(α-β) Han Shao, Shuo Xie, Kunhe Yang
In Proceedings of the 42nd International Conference on Machine Learning (ICML 2025)
[arXiv]
Platforms for Efficient and Incentive-Aware Collaboration
(α-β) Nika Haghtalab, Mingda Qiao, Kunhe Yang
In Proceedings of the ACM-SIAM Symposium on Discrete Algorithms (SODA 2025)
Presented at the 2024 ESIF Economics and AI+ML Meeting & TTIC Workshop on Incentives for Collaborative Learning and Data Sharing (Spotlight)
[arXiv] [conference version]
Is Knowledge Power? On the (Im)possibility of Learning from Strategic Interactions
(α-β) Nivasini Ananthakrishnan, Nika Haghtalab, Chara Podimata, Kunhe Yang
In Proceedings of the 38th Annual Conference on Neural Information Processing Systems (NeurIPS 2024)
[arXiv] [conference version]
Truthfulness of Calibration Measures
(α-β) Nika Haghtalab, Mingda Qiao, Kunhe Yang, Eric Zhao
In Proceedings of the 38th Annual Conference on Neural Information Processing Systems (NeurIPS 2024)
[arXiv] [conference version]
Strategic Littlestone Dimension: Improved Bounds on Online Strategic Classification
(α-β) Saba Ahmadi, Kunhe Yang, Hanrui Zhang
In Proceedings of the 38th Annual Conference on Neural Information Processing Systems (NeurIPS 2024)
[arXiv] [conference version]
Computational Aspects of Bayesian Persuasion under Approximate Best Response
(α-β) Kunhe Yang, Hanrui Zhang
In Proceedings of the 38th Annual Conference on Neural Information Processing Systems (NeurIPS 2024)
[arXiv] [conference version]
Calibrated Stackelberg Games: Learning Optimal Commitments Against Calibrated Agents
(α-β) Nika Haghtalab, Chara Podimata, Kunhe Yang
In Proceedings of the 37th Annual Conference on Neural Information Processing Systems (NeurIPS 2023)
Presented at the 2024 ESIF Economics and AI+ML Meeting
Selected for NeurIPS spotlight presentation
[arXiv] [conference version]
Fundamental Bounds on Online Strategic Classification
(α-β) Saba Ahmadi, Avrim Blum, Kunhe Yang
In Proceedings of the 24th ACM Conference on Economics and Computation (EC 2023)
[arXiv] [conference version]
Optimal Conservative Offline RL with General Function Approximation via Augmented Lagrangian
Paria Rashidinejad, Hanlin Zhu, Kunhe Yang, Stuart Russell, Jiantao Jiao
In Proceedings of the 11th International Conference on Learning Representations (ICLR 2023)
Selected for ICLR spotlight presentation
[arXiv] [conference version]
Oracle-Efficient Online Learning for Smoothed Adversaries
(α-β) Nika Haghtalab, Yanjun Han, Abhishek Shetty, Kunhe Yang
In Proceedings of the 36th Annual Conference on Neural Information Processing Systems (NeurIPS 2022)
Selected for NeurIPS oral presentation
[arXiv] [conference version]
Nudge: Stochastically Improving upon FCFS
Isaac Grosof, Kunhe Yang, Ziv Scully, Mor Harchol-Balter
In Proceedings of the ACM Measurement and Analysis of Computer Systems (SIGMETRICS 2021)
Sigmetrics 2021 Best Paper Award
[arXiv] [conference version]
Q-learning with Logarithmic Regret
Kunhe Yang, Lin Yang, Simon Du
In Proceedings of the 24th International Conference on Artificial Intelligence and Statistics (AISTATS 2021)
[arXiv] [conference version]
