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

10/28/2019 ∙ by Mingrui Zhang, et al. ∙ 16

In this paper, we propose three online algorithms for submodular maximisation. The first one, Mono-Frank-Wolfe, reduces the number of per-function gradient evaluations from T^1/2 [Chen2018Online] and T^3/2 [chen2018projection] to 1, and achieves a (1-1/e)-regret bound of O(T^4/5). The second one, Bandit-Frank-Wolfe, is the first bandit algorithm for continuous DR-submodular maximization, which achieves a (1-1/e)-regret bound of O(T^8/9). Finally, we extend Bandit-Frank-Wolfe to a bandit algorithm for discrete submodular maximization, Responsive-Frank-Wolfe, which attains a (1-1/e)-regret bound of O(T^8/9) in the responsive bandit setting.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.