A Stochastic Non-monotone DR-Submodular Maximization Problem over a Convex Set

被引：2
|
作者：
Lian, Yuefang [1 ]
Xu, Dachuan [1 ]
Du, Donglei [2 ]
Zhou, Yang [3 ]
机构：
[1] Beijing Univ Technol, Beijing Inst Sci & Engn Comp, Beijing 100124, Peoples R China
[2] Univ New Brunswick, Fac Management, Fredericton, NB E3B 9Y2, Canada
[3] Shandong Normal Univ, Sch Math & Stat, Jinan, Shandong, Peoples R China
来源：
COMPUTING AND COMBINATORICS, COCOON 2022 | 2022年 / 13595卷
基金：
芬兰科学院; 中国国家自然科学基金; 北京市自然科学基金; 加拿大自然科学与工程研究理事会;
关键词：
Stochastic optimization; Continuous DR-submodular; Frank-Wolfe algorithm; Potential function; Gradient estimator; MINIMIZATION;
D O I：
10.1007/978-3-031-22105-7_1
中图分类号：
TP39 [计算机的应用];
学科分类号：
081203 ; 0835 ;
摘要：
In this paper, we concentrate on a stochastic non-monotone DR-submodular maximization problem over a convex constraint C, where the objective function arises as an expectation of a set of stochastic functions. We develop an algorithm named SPIDER-FW, which is a stochastic version of the classical Frank-Wolfe algorithm with 1/4 (1- min(x epsilon C) parallel to x parallel to(infinity))F(x*) - epsilon (in expectation) approximation guarantee, the best guarantee so far for the above setting, achieved with O(1/epsilon) iterations, and O(1/epsilon(2)) first-order oracle calls.
引用
收藏
页码：1 / 11
页数：11
相关论文
共 50 条
  • [1] Non-monotone DR-submodular Maximization over General Convex Sets
    Durr, Christoph
    Nguyen Kim Thang
    Srivastav, Abhinav
    Tible, Leo
    PROCEEDINGS OF THE TWENTY-NINTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2020, : 2148 - 2154
  • [2] Online Non-Monotone DR-Submodular Maximization
    Nguyen Kim Thang
    Srivastav, Abhinav
    THIRTY-FIFTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THIRTY-THIRD CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE AND THE ELEVENTH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2021, 35 : 9868 - 9876
  • [3] Non-Monotone DR-Submodular Function Maximization
    Soma, Tasuku
    Yoshida, Yuichi
    THIRTY-FIRST AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2017, : 898 - 904
  • [4] Parallel Algorithm for Non-Monotone DR-Submodular Maximization
    Ene, Alina
    Nguyen, Huy L.
    INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 119, 2020, 119
  • [5] Parallel Algorithm for Non-Monotone DR-Submodular Maximization
    Ene, Alina
    Nguyen, Huy L.
    25TH AMERICAS CONFERENCE ON INFORMATION SYSTEMS (AMCIS 2019), 2019,
  • [6] Optimal Algorithms for Continuous Non-monotone Submodular and DR-Submodular Maximization
    Niazadeh, Rad
    Roughgarden, Tim
    Wang, Joshua R.
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 31 (NIPS 2018), 2018, 31
  • [7] Optimal algorithms for continuous non-monotone submodular and DR-submodular maximization
    Niazadeh, Rad
    Roughgarden, Tim
    Wang, Joshua R.
    Journal of Machine Learning Research, 2020, 21
  • [8] Optimal Algorithms for Continuous Non-monotone Submodular and DR-Submodular Maximization
    Niazadeh, Rad
    Roughgarden, Tim
    Wang, Joshua R.
    JOURNAL OF MACHINE LEARNING RESEARCH, 2020, 21
  • [9] Profit maximization in social networks and non-monotone DR-submodular maximization
    Gu, Shuyang
    Gao, Chuangen
    Huang, Jun
    Wu, Weili
    THEORETICAL COMPUTER SCIENCE, 2023, 957
  • [10] Resolving the Approximability of Offline and Online Non-monotone DR-Submodular Maximization over General Convex Sets
    Mualem, Loay
    Feldman, Moran
    INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 206, 2023, 206
12345