Approximate Weighted CR Coded Matrix Multiplication

by   Neophytos Charalambides, et al.

One of the most common, but at the same time expensive operations in linear algebra, is multiplying two matrices A and B. With the rapid development of machine learning and increases in data volume, performing fast matrix intensive multiplications has become a major hurdle. Two different approaches to overcoming this issue are, 1) to approximate the product; and 2) to perform the multiplication distributively. A CR-multiplication is an approximation where columns and rows of A and B are respectively sampled with replacement. In the distributed setting, multiple workers perform matrix multiplication subtasks in parallel. Some of the workers may be stragglers, meaning they do not complete their task in time. We present a novel approximate weighted CR coded matrix multiplication scheme, that achieves improved performance for distributed matrix multiplication.


page 1

page 2

page 3

page 4


Cuboid Partitioning for Hierarchical Coded Matrix Multiplication

Coded matrix multiplication is a technique to enable straggler-resistant...

Stark: Fast and Scalable Strassen's Matrix Multiplication using Apache Spark

This paper presents a new fast, highly scalable distributed matrix multi...

OverSketch: Approximate Matrix Multiplication for the Cloud

We propose OverSketch, an approximate algorithm for distributed matrix m...

Localized sketching for matrix multiplication and ridge regression

We consider sketched approximate matrix multiplication and ridge regress...

A Novel Matrix-Encoding Method for Privacy-Preserving Neural Networks (Inference)

In this work, we present , a novel matrix-encoding method that is partic...

Matrix Multiplication and Binary Space Partitioning Trees : An Exploration

Herein we explore a dual tree algorithm for matrix multiplication of A∈ℝ...

ATLAS: Interactive and Educational Linear Algebra System Containing Non-Standard Methods

While there are numerous linear algebra teaching tools, they tend to be ...