Provides the first regret guarantees for capacity-constrained delayed OCO under convex and strongly convex losses via randomized schedulers and Delayed-Weighted FTRL, recovering standard rates for C = Omega(log T) in the full-information case.
Bandit convex optimisation
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
years
2026 7representative citing papers
OGD achieves O(sqrt(T)) regret on hidden-convex losses via sharper algorithmic equivalence under Hessian compatibility, with a matching lower bound and O(T^{3/4}) bandit extension.
TP-VR-OPT achieves O(√(d E[S_T])) prediction-adaptive regret in two-point bandit convex optimization, with a matching Ω(√E[S_T]) lower bound up to √d, while single-point feedback cannot benefit from predictions.
ORBIT learns the (β-1)-smooth oracle price map via local polynomial approximation and bandit convex optimization in a semiparametric contextual pricing model, achieving regret Õ(T^{(2β-1)/(4β-3)} + √(dT)) with a matching lower bound for fixed d.
The paper establishes equilibrium existence and uniqueness for nonlinear utility consumer networks under contraction conditions and proposes a shape-constrained isotonic regression approach with strict no-regret convergence for learning utilities in targeted monopoly pricing.
The paper establishes the first tilde O(epsilon^{-1}) upper bounds and matching lower bounds for forward-KL-regularized offline contextual bandits under single-policy concentrability in both tabular and general function approximation settings.
Random team assignments in a professional firm reveal that indirect ties strongly increase new direct tie formation, while effects of degree and local density are smaller and less robust.
citing papers explorer
-
Capacity-Constrained Online Convex Optimization with Delayed Feedback
Provides the first regret guarantees for capacity-constrained delayed OCO under convex and strongly convex losses via randomized schedulers and Delayed-Weighted FTRL, recovering standard rates for C = Omega(log T) in the full-information case.
-
Online Learning on Hidden-Convex Losses via Algorithmic Equivalence: Optimal Regret, Geometric Barrier, and Bandit Feedback
OGD achieves O(sqrt(T)) regret on hidden-convex losses via sharper algorithmic equivalence under Hessian compatibility, with a matching lower bound and O(T^{3/4}) bandit extension.
-
Bandit Convex Optimization with Gradient Prediction Adaptivity
TP-VR-OPT achieves O(√(d E[S_T])) prediction-adaptive regret in two-point bandit convex optimization, with a matching Ω(√E[S_T]) lower bound up to √d, while single-point feedback cannot benefit from predictions.
-
Harnessing Unimodality in Semiparametric Contextual Pricing via Oracle Price Map Learning
ORBIT learns the (β-1)-smooth oracle price map via local polynomial approximation and bandit convex optimization in a semiparametric contextual pricing model, achieving regret Õ(T^{(2β-1)/(4β-3)} + √(dT)) with a matching lower bound for fixed d.
-
Equilibrium and Pricing in Consumer Networks with Nonlinear Utilities: An Online Shape-Constrained Learning Approach
The paper establishes equilibrium existence and uniqueness for nonlinear utility consumer networks under contraction conditions and proposes a shape-constrained isotonic regression approach with strict no-regret convergence for learning utilities in targeted monopoly pricing.
-
Fast Rates for Offline Contextual Bandits with Forward-KL Regularization under Single-Policy Concentrability
The paper establishes the first tilde O(epsilon^{-1}) upper bounds and matching lower bounds for forward-KL-regularized offline contextual bandits under single-policy concentrability in both tabular and general function approximation settings.
-
Causal inference for social network formation
Random team assignments in a professional firm reveal that indirect ties strongly increase new direct tie formation, while effects of degree and local density are smaller and less robust.