Corpus ID: 53111244

Maximizing Monotone DR-submodular Continuous Functions by Derivative-free Optimization

@article{Zhang2018MaximizingMD,
  title={Maximizing Monotone DR-submodular Continuous Functions by Derivative-free Optimization},
  author={Yibo Zhang and Chao Qian and Ke Tang},
  journal={ArXiv},
  year={2018},
  volume={abs/1810.06833}
}
  • Yibo Zhang, Chao Qian, Ke Tang
  • Published in ArXiv 2018
  • Mathematics, Computer Science
  • In this paper, we study the problem of monotone (weakly) DR-submodular continuous maximization. While previous methods require the gradient information of the objective function, we propose a derivative-free algorithm LDGM for the first time. We define $\beta$ and $\alpha$ to characterize how close a function is to continuous DR-submodulr and submodular, respectively. Under a convex polytope constraint, we prove that LDGM can achieve a $(1-e^{-\beta}-\epsilon)$-approximation guarantee after $O… CONTINUE READING

    Create an AI-powered research feed to stay up to date with new papers like this posted to ArXiv

    3
    Twitter Mentions

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 23 REFERENCES

    Maximizing Monotone Submodular Functions over the Integer Lattice

    VIEW 12 EXCERPTS
    HIGHLY INFLUENTIAL

    Submodular functions: from discrete to continuous domains

    VIEW 1 EXCERPT