arXiv · 2611.11808
Efficient Online Submodular Maximization with Bandit Feedback
Abstract
We study online monotone submodular maximization under a cardinality constraint with bandit feedback. On each round, the learner selects at most $k$ elements from a ground set of size $n$ and observes only the value of the selected set. We develop an efficient algorithm achieving $O\!\left(k\sqrt{nT\log(n/k)}\right)$ expected $(1-1/e)$-regret over $T$ rounds. To our knowledge, this is the first polynomial-time algorithm with $\sqrt{T}$ dependence on the horizon for arbitrary monotone submodular functions in the bandit setting. Our approach uses randomized sampling and a carefully constructed potential to reduce online submodular maximization to online linear optimization over the probability simplex.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Iasonas Nikolaou, Evimaria Terzi. 2026-11-09. Efficient Online Submodular Maximization with Bandit Feedback. https://searcharxiv.com/abs/2611.11808
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.