No-regret algorithms for online $k$-submodular maximization

Tasuku Soma

No-regret algorithms for online $k$-submodular maximization

Data Structures and Algorithms 2018-07-16 v1

Authors: Tasuku Soma

Abstract

We present a polynomial time algorithm for online maximization of $k$ -submodular maximization. For online (nonmonotone) $k$ -submodular maximization, our algorithm achieves a tight approximate factor in an approximate regret. For online monotone $k$ -submodular maximization, our approximate-regret matches to the best-known approximation ratio, which is tight asymptotically as $k$ tends to infinity. Our approach is based on the Blackwell approachability theorem and online linear optimization.

Keywords

online learning submodular maximization approximation algorithm

Cite

@article{arxiv.1807.04965,
  title  = {No-regret algorithms for online $k$-submodular maximization},
  author = {Tasuku Soma},
  journal= {arXiv preprint arXiv:1807.04965},
  year   = {2018}
}

Related papers

View all related →