4 papers
GoT-CD: Graph-of-Thoughts Causal Discovery and the Fragility of Post-hoc Path-Specific Fairness Audits
Nitish Nagesh, Elahe Khatibi, Thomas Dean Hughes +3
Causal discovery recovers directed structure from observational data and is increasingly used in clinical settings to support mechanism reasoning and fairness audits of predictive…
Randomized Least Squares Value Iteration itself is Joint Differentially Private
Haiyang Lu, Pratik Gajane, Shaojie Bai +1
As reinforcement learning (RL) increasingly applies to sensitive domains, such as health care and recommendation systems, privacy-preserving techniques have become essential to pro…
Best-of-Both-Worlds Multi-Dueling Bandits: Unified Algorithms for Stochastic and Adversarial Preferences under Condorcet and Borda Objectives
S Akash, Pratik Gajane, Jawar Singh
Multi-dueling bandits, where a learner selects arms per round and observes only the winner, arise naturally in many applications including ranking and recommendation sys…
Evaluating Causal Discovery Algorithms for Path-Specific Fairness and Utility in Healthcare
Nitish Nagesh, Elahe Khatibi, Thomas Hughes +3
Causal discovery in health data faces evaluation challenges when ground truth is unknown. We address this by collaborating with experts to construct proxy ground-truth graphs, esta…