Efficient statistical estimation for a non-randomly distributed system with application to large-scale data neural network

作者：

Highlights：

• Efficient estimation for a non-randomly distributed system is proposed.

• The communication cost is significantly reduced.

• Theoretical properties are established under mild conditions.

• We apply the new method to the neural network with large-scale data.

摘要

•Efficient estimation for a non-randomly distributed system is proposed.•The communication cost is significantly reduced.•Theoretical properties are established under mild conditions.•We apply the new method to the neural network with large-scale data.

论文关键词：Distributed system,Communication-efficient,Efficient estimation,Neural network,Large-scale data

论文评审过程：Received 8 March 2021, Revised 30 September 2021, Accepted 18 February 2022, Available online 4 March 2022, Version of Record 8 March 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.116698