New ℓ∞-self-concordant analysis and Ville's-inequality martingale control yield an online confidence bound of O(√(d log t) + B√d), leading to variance-dependent MNL bandit regret with no K dependence and only asymptotic B dependence.
Dynamic assortment optimization with changing contextual information
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Improved Online Confidence Bounds for Multinomial Logistic Bandits
New ℓ∞-self-concordant analysis and Ville's-inequality martingale control yield an online confidence bound of O(√(d log t) + B√d), leading to variance-dependent MNL bandit regret with no K dependence and only asymptotic B dependence.