Projection-free decentralized online learning for submodular maximization over time-varying networks

MaRDI QIDQ4998943zbMATH OpenFDO

Authors Junlong Zhu, Qingtao Wu, Mingchuan Zhang, Ruijuan Zheng, Keqin Li

Publication date 9 July 2021

Full work available at URL https://jmlr.csail.mit.edu/papers/v22/18-407.html

zbMATH Keywords

expected regret boundFrank-Wolfe algorithmsubmodular maximization

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Online learning over a decentralized network through ADMM
• An accelerated distributed online gradient push-sum algorithm on time-varying directed networks
• Adaptive online distributed optimization in dynamic environments

Cites work

• An analysis of approximations for maximizing submodular set functions—I
• Best Algorithms for Approximating the Maximum of a Submodular Set Function
• Determinantal point processes for machine learning
• Distributed Online Optimization in Dynamic Environments Using Mirror Descent
• Distributed optimization and statistical learning via the alternating direction method of multipliers
• Distributed submodular maximization
• scientific article; zbMATH DE number 6474901 (Why is no real title available?)
• scientific article; zbMATH DE number 3635849 (Why is no real title available?)
• scientific article; zbMATH DE number 6159604 (Why is no real title available?)
• Maximizing Non-monotone Submodular Functions
• Online Distributed Convex Optimization on Dynamic Networks
• Randomized composable core-sets for distributed submodular maximization
• Some NP-complete problems in quadratic and nonlinear programming
• Stochastic conditional gradient methods: from convex minimization to submodular maximization

Cited in

(1)

• Online non-monotone diminishing return submodular maximization in the bandit setting

This page was built for publication: Projection-free decentralized online learning for submodular maximization over time-varying networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4998943)