Corpus ID: 2555684

Guaranteed Non-convex Optimization: Submodular Maximization over Continuous Domains

@inproceedings{Bian2017GuaranteedNO,
  title={Guaranteed Non-convex Optimization: Submodular Maximization over Continuous Domains},
  author={Andrew An Bian and Baharan Mirzasoleiman and Joachim M. Buhmann and Andreas Krause},
  booktitle={AISTATS},
  year={2017}
}
  • Andrew An Bian, Baharan Mirzasoleiman, +1 author Andreas Krause
  • Published in AISTATS 2017
  • Computer Science, Mathematics
  • Submodular continuous functions are a category of (generally) non-convex/non-concave functions with a wide spectrum of applications. We characterize these functions and demonstrate that they can be maximized efficiently with approximation guarantees. Specifically, i) We introduce the weak DR property that gives a unified characterization of submodularity for all set, integer-lattice and continuous functions; ii) for maximizing monotone DR-submodular continuous functions under general down… CONTINUE READING

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

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 65 CITATIONS

    Universally Stable Cache Networks

    VIEW 18 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    Bounding Inefficiency of Equilibria in Continuous Actions Games using Submodularity and Curvature

    VIEW 10 EXCERPTS
    CITES BACKGROUND, RESULTS & METHODS
    HIGHLY INFLUENCED

    Competitive Algorithms for Online Budget-Constrained Continuous DR-Submodular Problems

    VIEW 6 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    Decentralized Gradient Tracking for Continuous DR-Submodular Maximization

    VIEW 13 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

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

    VIEW 5 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    Provable Non-Convex Optimization and Algorithm Validation via Submodularity

    VIEW 51 EXCERPTS
    CITES BACKGROUND, RESULTS & METHODS
    HIGHLY INFLUENCED

    Stochastic Conditional Gradient++

    VIEW 12 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    Unconstrained submodular maximization with constant adaptive complexity

    VIEW 15 EXCERPTS
    CITES BACKGROUND
    HIGHLY INFLUENCED

    Decentralized Submodular Maximization: Bridging Discrete and Continuous Settings

    VIEW 7 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    Distributed optimization for control and learning

    VIEW 7 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    FILTER CITATIONS BY YEAR

    2016
    2020

    CITATION STATISTICS

    • 23 Highly Influenced Citations

    • Averaged 19 Citations per year from 2017 through 2019

    • 9% Increase in citations per year in 2019 over 2018

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 45 REFERENCES