conftrace_

information theoretical

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

iterative dpo (1) policy improvement oracle (1) rejection sampling strategy (1) reverse-kl regularized contextual bandit (1) finite-sample guarantee (1) divergence measure (1) entropy estimation (1) independent subspace analysis (1) mutual information (1)

Papers

Iterative Preference Learning from Human Feedback: Bridging Theory and Practice for RLHF under KL-constraint ICML 2024 Information Theoretical Estimators Toolbox JMLR 2014