Affiliation:
1. Northeastern University, Boston, MA, USA
Abstract
As edge computing capabilities increase, model learning deployments in a heterogeneous edge environment have emerged. We consider an experimental design network, as introduced by Liu et al., in which network routing and rate allocation is designed to aid the transfer of data from sensors to heterogeneous learners. We generalize this setting by considering heterogeneous noisy Gaussian sources, incorporating multicast, but also-crucially-distributed algorithms in this setting. From a technical standpoint, we show that, assuming Gaussian sensor sources still yields an continuous DR-submodular experimental design objective. We also propose a distributed Frank-Wolfe algorithm yielding allocations within a 1-1/e factor from the optimal. Numerical evaluations show that our proposed algorithm outperforms competitors w.r.t. both objective maximization and model learning quality.
Publisher
Association for Computing Machinery (ACM)
Subject
Computer Networks and Communications,Hardware and Architecture,Software
Reference8 articles.
1. Mobile Edge Computing: A Survey
2. Convex Optimization
3. Stability of primal–dual gradient dynamics and applications to network optimization
4. Stochastic Processes
5. H. Hassani , M. Soltanolkotabi , and A. Karbasi . Gradient methods for submodular maximization . In NeurIPS , pages 5843 -- 5853 , 2017 . H. Hassani, M. Soltanolkotabi, and A. Karbasi. Gradient methods for submodular maximization. In NeurIPS, pages 5843--5853, 2017.