A comprehensive survey on coded distributed computing: Fundamentals, challenges, and networking applications

JS Ng, WYB Lim, NC Luong, Z Xiong… - … Surveys & Tutorials, 2021 - ieeexplore.ieee.org
Distributed computing has become a common approach for large-scale computation tasks
due to benefits such as high reliability, scalability, computation speed, and cost …

Private retrieval, computing, and learning: Recent progress and future challenges

S Ulukus, S Avestimehr, M Gastpar… - IEEE Journal on …, 2022 - ieeexplore.ieee.org
Most of our lives are conducted in the cyberspace. The human notion of privacy translates
into a cyber notion of privacy on many functions that take place in the cyberspace. This …

Federated learning with buffered asynchronous aggregation

J Nguyen, K Malik, H Zhan… - International …, 2022 - proceedings.mlr.press
Scalability and privacy are two critical concerns for cross-device federated learning (FL)
systems. In this work, we identify that synchronous FL–cannot scale efficiently beyond a few …

Lagrange coded computing: Optimal design for resiliency, security, and privacy

Q Yu, S Li, N Raviv, SMM Kalan… - The 22nd …, 2019 - proceedings.mlr.press
We consider a scenario involving computations over a massive dataset stored distributedly
across multiple workers, which is at the core of distributed learning algorithms. We propose …

Polynomial codes: an optimal design for high-dimensional coded matrix multiplication

Q Yu, M Maddah-Ali… - Advances in Neural …, 2017 - proceedings.neurips.cc
We consider a large-scale matrix multiplication problem where the computation is carried
out using a distributed system with a master node and multiple worker nodes, where each …

Short-dot: Computing large linear transforms distributedly using coded short dot products

S Dutta, V Cadambe, P Grover - Advances In Neural …, 2016 - proceedings.neurips.cc
Faced with saturation of Moore's law and increasing size and dimension of data, system
designers have increasingly resorted to parallel and distributed computing to reduce …

On the optimal recovery threshold of coded matrix multiplication

S Dutta, M Fahim, F Haddadpour… - IEEE Transactions …, 2019 - ieeexplore.ieee.org
We provide novel coded computation strategies for distributed matrix-matrix products that
outperform the recent “Polynomial code” constructions in recovery threshold, ie, the required …

Coded computation over heterogeneous clusters

A Reisizadeh, S Prakash, R Pedarsani… - IEEE Transactions …, 2019 - ieeexplore.ieee.org
In large-scale distributed computing clusters, such as Amazon EC2, there are several types
of “system noise” that can result in major degradation of performance: system failures …

Communication-computation efficient gradient coding

M Ye, E Abbe - International Conference on Machine …, 2018 - proceedings.mlr.press
This paper develops coding techniques to reduce the running time of distributed learning
tasks. It characterizes the fundamental tradeoff to compute gradients in terms of three …

GASP codes for secure distributed matrix multiplication

RGL D'Oliveira, S El Rouayheb… - IEEE Transactions on …, 2020 - ieeexplore.ieee.org
We consider the problem of secure distributed matrix multiplication (SDMM) in which a user
wishes to compute the product of two matrices with the assistance of honest but curious …