Introduces P2MLE-UCB and GP2-UCB round-based algorithms achieving optimal regret bounds for multiplicative and general position-aware MNL bandits, with efficient optimization subroutines.
Learning an optimal assortment policy under observational data
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
New algorithms for joint contextual MNL assortment and pricing deliver improved online regret bounds of order W sqrt(d T log N)/L0 and local suboptimality guarantees offline.
Pairing new products with top incumbents and exploring multiple new products simultaneously up to a potential-based threshold is optimal for minimizing regret in assortment-based social learning.
citing papers explorer
-
Learning in Position-Aware Multinomial Logit Bandits: From Multiplicative to General Position Effects
Introduces P2MLE-UCB and GP2-UCB round-based algorithms achieving optimal regret bounds for multiplicative and general position-aware MNL bandits, with efficient optimization subroutines.
-
Optimal Online and Offline Algorithms for Contextual MNL with Applications to Assortment and Pricing
New algorithms for joint contextual MNL assortment and pricing deliver improved online regret bounds of order W sqrt(d T log N)/L0 and local suboptimality guarantees offline.
-
Optimal Exploration of New Products under Assortment Decisions
Pairing new products with top incumbents and exploring multiple new products simultaneously up to a potential-based threshold is optimal for minimizing regret in assortment-based social learning.