Log-barrier regularized stochastic mirror descent yields Lai–Wei stable bandit sampling, valid Wald intervals, near-optimal regret up to logs, and asymptotic normality under o(√T) corruption.
Title resolution pending
1 Pith paper cite this work, alongside 50 external citations. Polarity classification is still indexing.
1
Pith paper citing it
50
external citations · OpenAlex
fields
stat.ML 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Stabilizing Bandits using Regularization: Precise Regret and A Quantitative Central Limit Theorem
Log-barrier regularized stochastic mirror descent yields Lai–Wei stable bandit sampling, valid Wald intervals, near-optimal regret up to logs, and asymptotic normality under o(√T) corruption.