Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/William Overman

William Overman

4 indexed papers

Recent (6 mo)
4
With code
0
Influential cites
0
Benchmarked
0

Publications per year

4
26

Top categories

AI×4ML×2

Frequent co-authors

Mohsen Bayati4×

Research Timeline

2026
Calibrating Conservatism for Scalable Oversight

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.

Calibrating Conservatism for Scalable Oversight

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.

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 sampling near-optimal actions.

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 sampling near-optimal actions.

Highlighted terms show continued research focus across papers

Papers

cs.LGcs.AIRecentMay 29, 2026

Annealed Softmax Greedy in Many-Armed Bayesian Bandits

William Overman, Mohsen Bayati

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…

View →
cs.LGcs.AIRecentMay 29, 2026

Annealed Softmax Greedy in Many-Armed Bayesian Bandits

William Overman, Mohsen Bayati

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…

View →
cs.AIRecentMay 27, 2026

Calibrating Conservatism for Scalable Oversight

William Overman, Mohsen Bayati

The paper introduces Calibrated Collective Oversight (CCO), a novel framework that uses aggregated auxiliary scoring functions and Conformal Decision Theory to provide statistically guaranteed, scalab…

View →
cs.AIRecentMay 27, 2026

Calibrating Conservatism for Scalable Oversight

William Overman, Mohsen Bayati

The paper introduces Calibrated Collective Oversight (CCO), a novel framework that uses aggregated auxiliary scoring functions and Conformal Decision Theory to provide statistically guaranteed, scalab…

View →