On prediction from expert advice with more than five experts

Abstract:We prove that no single rank ordered adversary strategy is globally optimal for the prediction with expert advice problem with six or more experts, in both the geometric stopping and finite time horizon settings. The proof is based on establishing a leading order correction when one expert moves far ahead of the others. This allows us to connect optimal strategies between $n$ and $j<n$ experts and utilize recent results on the exact optimality set for the five expert problem.

42 pages. Lean formalization: this https URL

Analysis of PDEs (math.AP); Computer Science and Game Theory (cs.GT); Machine Learning (cs.LG); Optimization and Control (math.OC)

arXiv:2610.05186 [math.AP]

(or arXiv:2610.05186v1 [math.AP] for this version)

https://doi.org/10.48550/arXiv.2610.05186 Focus to learn more arXiv-issued DOI via DataCite (pending registration)

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.