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.
arXiv preprint arXiv:1702.02896 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
stat.ME 2years
2026 2representative citing papers
citing papers explorer
-
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.
- Causal Stability Selection