Optimal reward distributions for best-of-n sampling at fixed KL divergence
Authors
- Kundan Baliga
- Aditya Byju
- Aiden Xie
Institutions
- Georgia Institute of Technology (US)
- University of Illinois Urbana-Champaign (US)
Publication Details
- Journal
- Zenodo (CERN European Organization for Nuclear Research)
- Published
- 2026-11-17
- DOI
- https://doi.org/10.5281/zenodo.24327025
- Primary Topic
- Advanced Bandit Algorithms Research
- Type
- preprint