Establishes maximal concentration bounds for stochastic approximation under heavy-tailed Markovian noise, with tails ranging from sub-Gaussian to heavier than Weibull depending on step sizes and contractivity properties, plus a truncation argument for unbounded noise.
Foundations and Trends
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
years
2026 6representative citing papers
Active sampling with allocation q_j proportional to p_j to the 2/3 achieves tight regret sqrt(n/T) times norm of p to the 2/3 for known context distribution p, with improvement up to Theta(k to the 1/4) over passive sampling.
Consumers transfer brand-level regularities across contexts using low-D boundedly rational meta-learning approximations that fit choice data better than no-transfer or fully integrated Bayesian benchmarks.
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.
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.
CAGE uses common-agency games and an EPEC algorithm to compute equilibrium policies that balance multiple conflicting objectives for test-time LLM alignment.
citing papers explorer
-
Concentration of General Stochastic Approximation Under Heavy-Tailed Markovian Noise
Establishes maximal concentration bounds for stochastic approximation under heavy-tailed Markovian noise, with tails ranging from sub-Gaussian to heavier than Weibull depending on step sizes and contractivity properties, plus a truncation argument for unbounded noise.
-
Active Context Selection Improves Simple Regret in Contextual Bandits
Active sampling with allocation q_j proportional to p_j to the 2/3 achieves tight regret sqrt(n/T) times norm of p to the 2/3 for known context distribution p, with improvement up to Theta(k to the 1/4) over passive sampling.
-
Boundedly Rational Meta-Learning in Sequential Consumer Choice
Consumers transfer brand-level regularities across contexts using low-D boundedly rational meta-learning approximations that fit choice data better than no-transfer or fully integrated Bayesian benchmarks.
-
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.
-
Common-agency Games for Multi-Objective Test-Time Alignment
CAGE uses common-agency games and an EPEC algorithm to compute equilibrium policies that balance multiple conflicting objectives for test-time LLM alignment.