Paper-Conference

Conformal Arbitrage - Risk-Controlled Balancing of Competing Objectives in Language Models

Can We Validate Counterfactual Estimations in the Presence of General Network Interference?

Aligning Model Properties via Conformal Risk Control

Higher-Order Causal Message Passing for Experimentation with Complex Interference

Improved Regret Bound for Safe Reinforcement Learning via Tighter Cost Pessimism and Reward Optimism

Beating Price of Anarchy and Gradient Descent without Regret in Potential Games

Global Convergence of Multi-Agent Policy Gradient in Markov Potential Games

Independent Natural Policy Gradient always converges in Markov Potential Games