2026.08
Planning Against Learning in Rank-1 Games
Publications
2026
2026.08
Annealed Softmax Greedy in Many-Armed Bayesian Bandits
2026.07
Calibrating Conservatism for Scalable Oversight
2026.07
The Oversight Game: Learning to Cooperatively Balance an AI Agent's Safety and Autonomy
2026.04
Occupancy Prediction with Patient Data: Evaluating Time-Series, Patient-Level Aggregation, and Deep Set Models
2026.03
Causal Effects with Unobserved Unit Types in Interacting Human–AI Systems
2025
2025.12
Conformal Arbitrage: Risk-Controlled Balancing of Competing Objectives in Language Models
2025.09
On Aligning Prediction Models with Clinical Experiential Learning: A Prostate Cancer Case Study
2025.08
Improved Regret Bound for Safe Reinforcement Learning via Tighter Cost Pessimism and Reward Optimism
2025.02
Can We Validate Counterfactual Estimations in the Presence of General Network Interference?
2024
2024.12
Aligning Model Properties via Conformal Risk Control
2024.12
Higher-Order Causal Message Passing for Experimentation with Complex Interference
2024.05
Beating Price of Anarchy and Gradient Descent without Regret in Potential Games
2022
2022.04
Global Convergence of Multi-Agent Policy Gradient in Markov Potential Games
2022.03
Independent Natural Policy Gradient Always Converges in Markov Potential Games
2018
2018.05
Some Ordered Ramsey Numbers of Graphs on Four Vertices