theoretical study
- Efficient and Near-Optimal Algorithm for Contextual Dueling Bandits with Offline Regression Oracles
- On the Sample Complexity of Differentially Private Policy Optimization
- Unlabeled Data Can Provably Enhance In-Context Learning of Transformers
- When Models Don’t Collapse: On the Consistency of Iterative MLE
- Why Playing Against Diverse and Challenging Opponents Speeds Up Coevolution: A Theoretical Analysis on Combinatorial Games