Alignment between AI and human confidence reduces the complexity of learning optimal binary decisions with AI assistance, lowering regret from Ω(√(|H|·|B|·T)) to O(√(|H|·T log T)) under perfect alignment.
(2012) we have that the expected regret E[R(T)] = Ω M·ϵ− ϵ2 √ M ·T 3/2 , which forϵ= Θ( p M/T)becomes E[R(T)] = Ω √ T·M = Ω s T· log(|Π|) logK !
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
Learning to Decide with AI Assistance under Human-Alignment
Alignment between AI and human confidence reduces the complexity of learning optimal binary decisions with AI assistance, lowering regret from Ω(√(|H|·|B|·T)) to O(√(|H|·T log T)) under perfect alignment.