William Overman
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper introduces Calibrated Collective Oversight (CCO), a novel framework that uses aggregated auxiliary scoring functions and Conformal Decision Theory to provide statistically guaranteed, scalable human oversight for powerful, autonomous AI agents.
The paper analyzes the performance of an annealed softmax policy in a Bayesian bandit setting, proving that under specific prior conditions, it achieves near-optimal regret rates by effectively sampling near-optimal actions.
Papers
Annealed Softmax Greedy in Many-Armed Bayesian Bandits
The paper analyzes the performance of an annealed softmax policy in a Bayesian bandit setting, proving that under specific prior conditions, it achieves near-optimal regret rates by effectively sampli…