Optimal reward distributions for best-of-n sampling at fixed KL divergence
Year: 2026
Type: preprint
Abstract: Anonymous version 1 of the manuscript.
Authors: Baliga, Kundan, Xie, Aiden, Byju, Aditya
Language: English
Field: Decision Sciences
Domain: Social Sciences
Open Access status: green
OpenAlex ID: W7235403191
