Distributed Black-Box Optimization via Error Correcting Codes
Distributed, Parallel, and Cluster Computing
2019-07-16 v1 Information Theory
Machine Learning
math.IT
Abstract
We introduce a novel distributed derivative-free optimization framework that is resilient to stragglers. The proposed method employs coded search directions at which the objective function is evaluated, and a decoding step to find the next iterate. Our framework can be seen as an extension of evolution strategies and structured exploration methods where structured search directions were utilized. As an application, we consider black-box adversarial attacks on deep convolutional neural networks. Our numerical experiments demonstrate a significant improvement in the computation times.
Cite
@article{arxiv.1907.05984,
title = {Distributed Black-Box Optimization via Error Correcting Codes},
author = {Burak Bartan and Mert Pilanci},
journal= {arXiv preprint arXiv:1907.05984},
year = {2019}
}