Communicationefficient distributed eigenspace estimation with arbitrary node failures
Abstract
We develop an eigenspace estimation algorithm for distributed environments with arbitrary node failures, where a subset of computing nodes can return structurally valid but otherwise arbitrarily chosen responses. Notably, this setting encompasses several important scenarios that arise in distributed computing and datacollection environments such as silent/soft errors, outliers or corrupted data at certain nodes, and adversarial responses. Our estimator builds upon and matches the performance of a recently proposed nonrobust estimator up to an additive $\tilde{O}(\sigma \sqrt{\alpha})$ error, where $\sigma^2$ is the variance of the existing estimator and $\alpha$ is the fraction of corrupted nodes.
 Publication:

arXiv eprints
 Pub Date:
 May 2022
 DOI:
 10.48550/arXiv.2206.00127
 arXiv:
 arXiv:2206.00127
 Bibcode:
 2022arXiv220600127C
 Keywords:

 Statistics  Machine Learning;
 Computer Science  Distributed;
 Parallel;
 and Cluster Computing;
 Computer Science  Machine Learning;
 Mathematics  Numerical Analysis
 EPrint:
 23 pages, 1 figure