A Learning-Based Approach to Approximate Coded Computation

被引：2

作者：

Agrawal, Navneet ^{[1
]}

Qiu, Yuqin ^{[2
]}

Frey, Matthias ^{[1
]}

Bjelakovic, Igor ^{[3
]}

Maghsudi, Setareh ^{[3
,4
]}

Stanczak, Slawomir ^{[1
,3
]}

Zhu, Jingge ^{[2
]}

机构：

[1] Tech Univ Berlin, Berlin, Germany

[2] Univ Melbourne, Dept Elect & Elect Engn, Melbourne, Vic, Australia

[3] Fraunhofer Heinrich Hertz Inst, Berlin, Germany

[4] Univ Tubingen, Dept Comp Sci, Tubingen, Germany

来源：

2022 IEEE INFORMATION THEORY WORKSHOP (ITW) | 2022年

基金：

澳大利亚研究理事会;

关键词：

D O I：

10.1109/ITW54588.2022.9965865

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Lagrange coded computation (LCC) is essential to solving problems about matrix polynomials in a coded distributed fashion; nevertheless, it can only solve the problems that are representable as matrix polynomials. In this paper, we propose AICC, an AI-aided learning approach that is inspired by LCC but also uses deep neural networks (DNNs). It is appropriate for coded computation of more general functions. Numerical simulations demonstrate the suitability of the proposed approach for the coded computation of different matrix functions that are often utilized in digital signal processing.

引用

页码：600 / 605

页数：6