Develops IPW-Z estimation framework for misspecified contextual bandits, establishing consistency and asymptotic normality under scaled inverse-propensity convergence for marginal moment targets.
Adaptive off-policy inference for M- estimators under model misspecification.arXiv preprint arXiv:2509.14218, 2025
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Constructs a time-indexed set S_t retaining the true optimal policy uniformly over time with high probability, enabling early stopping with sample complexity O((log |Π| + log log(1/Δ_min))/Δ_min²) when the optimum is unique.
citing papers explorer
-
Statistical Inference for Misspecified Contextual Bandits
Develops IPW-Z estimation framework for misspecified contextual bandits, establishing consistency and asymptotic normality under scaled inverse-propensity convergence for marginal moment targets.
-
Anytime-valid Optimal Policy Identification
Constructs a time-indexed set S_t retaining the true optimal policy uniformly over time with high probability, enabling early stopping with sample complexity O((log |Π| + log log(1/Δ_min))/Δ_min²) when the optimum is unique.