A Learning-Based Approach to Approximate Coded Computation

TL;DR

This paper introduces AICC, a learning-based method using deep neural networks to extend coded computation to a broader class of functions beyond matrix polynomials, demonstrated through numerical simulations.

Contribution

Proposes AICC, a novel AI-aided approach that generalizes coded computation to more functions using deep neural networks, building upon Lagrange coded computation.

Findings

Effective for coded computation of various matrix functions

Outperforms traditional methods in flexibility

Validated through numerical simulations

Abstract

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.