Skip to yearly menu bar Skip to main content


Poster

Near-Optimal Policies for Dynamic Multinomial Logit Assortment Selection Models

Yining Wang · Xi Chen · Yuan Zhou

Room 517 AB #102

Keywords: [ Learning Theory ] [ Online Learning ]


Abstract:

In this paper we consider the dynamic assortment selection problem under an uncapacitated multinomial-logit (MNL) model. By carefully analyzing a revenue potential function, we show that a trisection based algorithm achieves an item-independent regret bound of O(sqrt(T log log T), which matches information theoretical lower bounds up to iterated logarithmic terms. Our proof technique draws tools from the unimodal/convex bandit literature as well as adaptive confidence parameters in minimax multi-armed bandit problems.

Live content is unavailable. Log in and register to view live content