Orthonormal Sketches for Secure Coded Regression
This work addresses secure and efficient distributed linear regression for coded computing networks, representing an incremental advancement in combining existing techniques.
The paper tackles the problem of speeding up linear regression in distributed systems while ensuring security and straggler resilience, achieving improvements through a method that combines orthonormal sketching and block subsampling, as demonstrated in numerical experiments.
In this work, we propose a method for speeding up linear regression distributively, while ensuring security. We leverage randomized sketching techniques, and improve straggler resilience in asynchronous systems. Specifically, we apply a random orthonormal matrix and then subsample in \textit{blocks}, to simultaneously secure the information and reduce the dimension of the regression problem. In our setup, the transformation corresponds to an encoded encryption in an \textit{approximate} gradient coding scheme, and the subsampling corresponds to the responses of the non-straggling workers; in a centralized coded computing network. We focus on the special case of the \textit{Subsampled Randomized Hadamard Transform}, which we generalize to block sampling; and discuss how it can be used to secure the data. We illustrate the performance through numerical experiments.