Improved Online Learning Algorithm for Multinomial Logit Contextual Bandits release_afiy7i7wjvhfzdurjnng2u5owe

by Priyank Agrawal, Vashist Avadhanula, Theja Tulabandhula

Released as a article .

(2021)

Abstract

In this paper, we consider the contextual variant of the MNL-Bandit problem. More specifically, we consider a dynamic assortment optimization problem, where in every round a decision maker offers a subset (assortment) of products to a consumer, and observes their response. Consumers purchase products so as to maximize their utility. We assume that the products are described by a set of attributes and the mean utility of a product is linear in the values of these attributes. We model consumer choice behavior by means of the widely used Multinomial Logit (MNL) model, and consider the decision maker's problem of dynamically learning the model parameters, while optimizing cumulative revenue over the selling horizon T. Though this problem has attracted considerable attention in recent times, many existing methods and their theoretical performance depend on a problem dependent parameter which could be prohibitively large. In particular, existing algorithms for this problem have regret bounded by O(√(κ d T)), where κ is a problem dependent constant that can have exponential dependency on the number of attributes. In this paper, we propose a new algorithm with a carefully designed exploration strategy and show that the regret is bounded by O(√(dT) + κ), significantly improving the performance over existing methods.
In text/plain format

Archived Files and Locations

There are no accessible files associated with this release. You could check other releases for this work for an accessible version.

"Dark" Archived
Save Paper Now!

Know of a fulltext copy of on the public web? Submit a URL and we will archive it

Type  article
Stage   submitted
Date   2021-02-19
Version   v2
Language   en ?
arXiv  2011.14033v2
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: 0686de37-650f-4249-9180-3099a9fa72ce
API URL: JSON