The paper introduces model elasticity to bound the regret of contextual bandits with AI-imputed missing covariates, and shows that MAR-based calibration removes the dominant linear regret term.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Pre-Trained AI Model Assisted Online Decision-Making under Missing Covariates: A Theoretical Perspective
The paper introduces model elasticity to bound the regret of contextual bandits with AI-imputed missing covariates, and shows that MAR-based calibration removes the dominant linear regret term.