Submodular Bandit Problem Under Multiple Constraints

06/01/2020
by   Sho Takemori, et al.
0

The linear submodular bandit problem was proposed to simultaneously address diversified retrieval and online learning in a recommender system. If there is no uncertainty, this problem is equivalent to a submodular maximization problem under a cardinality constraint. However, in some situations, recommendation lists should satisfy additional constraints such as budget constraints, other than a cardinality constraint. Thus, motivated by diversified retrieval considering budget constraints, we introduce a submodular bandit problem under the intersection of l knapsacks and a k-system constraint. Here k-system constraints form a very general class of constraints including cardinality constraints and the intersection of k matroid constraints. To solve this problem, we propose a non-greedy algorithm that adaptively focuses on a standard or modified upper-confidence bound. We provide a high-probability upper bound of an approximation regret, where the approximation ratio matches that of a fast offline algorithm. Moreover, we perform experiments under various combinations of constraints using a synthetic and two real-world datasets and demonstrate that our proposed methods outperform the existing baselines.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/28/2019

Online Continuous Submodular Maximization: From Full-Information to Bandit Feedback

In this paper, we propose three online algorithms for submodular maximis...
research
05/21/2023

Bandit Multi-linear DR-Submodular Maximization and Its Applications on Adversarial Submodular Bandits

We investigate the online bandit learning of the monotone multi-linear D...
research
11/22/2018

Approximate Multi-Matroid Intersection via Iterative Refinement

We introduce a new iterative rounding technique to round a point in a ma...
research
07/18/2023

Submodular Maximization under the Intersection of Matroid and Knapsack Constraints

Submodular maximization arises in many applications, and has attracted a...
research
05/13/2019

An improved algorithm for the submodular secretary problem with a cardinality constraint

We study the submodular secretary problem with a cardinality constraint....
research
01/25/2020

Robust Submodular Minimization with Applications to Cooperative Modeling

Robust Optimization is becoming increasingly important in machine learni...
research
03/05/2020

Optimal matroid bases with intersection constraints: Valuated matroids, M-convex functions, and their applications

For two matroids M_1 and M_2 with the same ground set V and two cost fun...

Please sign up or login with your details

Forgot password? Click here to reset