paper-with-me

Papers

Encrypted accelerated least squares regression

2017-03-02 · Pedro M. Esperança, Louis J. M. Aslett, Chris C. Holmes

Information that is stored in an encrypted format is, by definition, usually not amenable to statistical analysis or machine learning methods. In this paper we present detailed analysis of coordinate and accelerated gradient descent algorithms which are capable of fitting least squares and penalised ridge regression models, using data encrypted under a fully homomorphic encryption scheme. Gradient descent is shown to dominate in terms of encrypted computational speed, and theoretical results are proven to give parameter bounds which ensure correctness of decryption. The characteristics of encrypted computation are empirically shown to favour a non-standard acceleration technique. This demonstrates the possibility of approximating conventional statistical regression methods using encrypted data without compromising privacy.

📄 PDF Abstract BibTeX arXiv:1703.00839

Code (0)

등록된 구현이 없습니다.

Tasks

regression

Similar Papers 제목 키워드 기반

Optimal Controller and Security Parameter for Encrypted Control Systems Under Least Squares Identification

2023-02-23 · Kaoru Teranishi, Kiminao Kogiso

Encrypted control is a framework for the secure outsourcing of controller computation using homomorphic encryption that allows to perform arithmetic operations on encrypted data without decryption. In a previous study, t…

Accelerated SGD for Non-Strongly-Convex Least Squares

2022-03-03 · Aditya Varre, Nicolas Flammarion

We consider stochastic approximation for the least squares regression problem in the non-strongly convex setting. We present the first practical algorithm that achieves the optimal prediction error rates in terms of depe…

regression

Accelerating Stochastic Gradient Descent For Least Squares Regression

2017-04-26 · Prateek Jain, Sham M. Kakade, Rahul Kidambi, Praneeth Netrapalli 외

There is widespread sentiment that it is not possible to effectively utilize fast gradient methods (e.g. Nesterov's acceleration, conjugate gradient, heavy ball) for the purposes of stochastic optimization due to their i…

regressionStochastic Optimization

Distributionally Robust Linear Regression With Block Lewis Weights

2026-06-30 · Naren Sarayu Manoj, Kumar Kshitij Patel arxiv

We present an algorithm for the group distributionally robust (GDR) least squares problem. Given $m$ groups, a parameter vector in $\mathbb{R}^d$, and stacked design matrices and responses $\mathbf{A}$ and $\mathbf{b}$, …

Sample Identifying Complexity of Encrypted Control Systems Under Least Squares Identification

2022-10-17 · Kaoru Teranishi, Kiminao Kogiso

A sample identifying complexity has been introduced in the previous study to capture an adversary's estimation error of system identification. The complexity plays a crucial role in defining the security of encrypted con…