LGJun 3, 2017

Thompson Sampling for the MNL-Bandit

arXiv:1706.00977v799 citations
Originality Incremental advance
AI Analysis

This addresses exploration-exploitation challenges in combinatorial bandit problems, with applications in domains like recommendation systems, but is incremental as it adapts an existing method to a specific model.

The paper tackles the MNL-Bandit problem, a sequential subset selection task under parameter uncertainty, by adapting Thompson Sampling to achieve near-optimal regret and strong numerical performance.

We consider a sequential subset selection problem under parameter uncertainty, where at each time step, the decision maker selects a subset of cardinality $K$ from $N$ possible items (arms), and observes a (bandit) feedback in the form of the index of one of the items in said subset, or none. Each item in the index set is ascribed a certain value (reward), and the feedback is governed by a Multinomial Logit (MNL) choice model whose parameters are a priori unknown. The objective of the decision maker is to maximize the expected cumulative rewards over a finite horizon $T$, or alternatively, minimize the regret relative to an oracle that knows the MNL parameters. We refer to this as the MNL-Bandit problem. This problem is representative of a larger family of exploration-exploitation problems that involve a combinatorial objective, and arise in several important application domains. We present an approach to adapt Thompson Sampling to this problem and show that it achieves near-optimal regret as well as attractive numerical performance.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes