Iterative Sketching for Secure Coded Regression
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916184904957952 |
|---|---|
| author | Charalambides, Neophytos Mahdavifar, Hessam Pilanci, Mert Hero III, Alfred O. |
| author_facet | Charalambides, Neophytos Mahdavifar, Hessam Pilanci, Mert Hero III, Alfred O. |
| contents | Linear regression is a fundamental and primitive problem in supervised machine learning, with applications ranging from epidemiology to finance. In this work, we propose methods for speeding up distributed linear regression. We do so by leveraging randomized techniques, while also ensuring security and straggler resiliency in asynchronous distributed computing systems. Specifically, we randomly rotate the basis of the system of equations and then subsample blocks, to simultaneously secure the information and reduce the dimension of the regression problem. In our setup, the basis rotation corresponds to an encoded encryption in an approximate gradient coding scheme, and the subsampling corresponds to the responses of the non-straggling servers in the centralized coded computing framework. This results in a distributive iterative stochastic approach for matrix compression and steepest descent. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2308_04185 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Iterative Sketching for Secure Coded Regression Charalambides, Neophytos Mahdavifar, Hessam Pilanci, Mert Hero III, Alfred O. Information Theory Cryptography and Security Distributed, Parallel, and Cluster Computing Machine Learning Numerical Analysis 65B99, 68P20, 68P25, 68P27, 68P30, 94-10, 94A11, 94A16, 94B60 E.3; E.4; F.2.1; G.1.3 Linear regression is a fundamental and primitive problem in supervised machine learning, with applications ranging from epidemiology to finance. In this work, we propose methods for speeding up distributed linear regression. We do so by leveraging randomized techniques, while also ensuring security and straggler resiliency in asynchronous distributed computing systems. Specifically, we randomly rotate the basis of the system of equations and then subsample blocks, to simultaneously secure the information and reduce the dimension of the regression problem. In our setup, the basis rotation corresponds to an encoded encryption in an approximate gradient coding scheme, and the subsampling corresponds to the responses of the non-straggling servers in the centralized coded computing framework. This results in a distributive iterative stochastic approach for matrix compression and steepest descent. |
| title | Iterative Sketching for Secure Coded Regression |
| topic | Information Theory Cryptography and Security Distributed, Parallel, and Cluster Computing Machine Learning Numerical Analysis 65B99, 68P20, 68P25, 68P27, 68P30, 94-10, 94A11, 94A16, 94B60 E.3; E.4; F.2.1; G.1.3 |
| url | https://arxiv.org/abs/2308.04185 |