A modular reduction from budget-constrained contextual bandits with adversarial contexts to unconstrained bandits via surrogate rewards, yielding improved guarantees and an efficient algorithm based on SquareCB.
Statistics & Probability Letters , volume=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
A projection-based algorithm for COCO achieves O(log T) regret and O(log T) CCV for strongly convex losses and O(sqrt(T)) for convex losses by leveraging self-contracted curves.
Establishes root-n consistency and asymptotic normality for the plug-in estimator of E[F_Y^{-1} ∘ F_Z(X)] under weaker conditions allowing unbounded support, plus a consistent variance estimator.
citing papers explorer
-
Constrained Contextual Bandits with Adversarial Contexts
A modular reduction from budget-constrained contextual bandits with adversarial contexts to unconstrained bandits via surrogate rewards, yielding improved guarantees and an efficient algorithm based on SquareCB.
-
Improved Guarantees for Constrained Online Convex Optimization via Self-Contraction
A projection-based algorithm for COCO achieves O(log T) regret and O(log T) CCV for strongly convex losses and O(sqrt(T)) for convex losses by leveraging self-contracted curves.
-
Asymptotic Properties of Empirical Quantile-Based Estimators
Establishes root-n consistency and asymptotic normality for the plug-in estimator of E[F_Y^{-1} ∘ F_Z(X)] under weaker conditions allowing unbounded support, plus a consistent variance estimator.