paper-with-me

홈 › Papers

Near Optimal Private and Robust Linear Regression

2023-01-30 · Xiyang Liu, Prateek Jain, Weihao Kong, Sewoong Oh, Arun Sai Suggala

We study the canonical statistical estimation problem of linear regression from $n$ i.i.d.~examples under $(\varepsilon,\delta)$-differential privacy when some response variables are adversarially corrupted. We propose a variant of the popular differentially private stochastic gradient descent (DP-SGD) algorithm with two innovations: a full-batch gradient descent to improve sample complexity and a novel adaptive clipping to guarantee robustness. When there is no adversarial corruption, this algorithm improves upon the existing state-of-the-art approach and achieves a near optimal sample complexity. Under label-corruption, this is the first efficient linear regression algorithm to guarantee both $(\varepsilon,\delta)$-DP and robustness. Synthetic experiments confirm the superiority of our approach.

📄 PDF Abstract BibTeX arXiv:2301.13273

Code (0)

등록된 구현이 없습니다.

Tasks

regression

Methods 이 논문이 사용한 방법론

Linear Regression Linear Regression is a method for modelling a relationship between a dependent variable and independent variables. These models can be fit with numerous approaches. The most…

Similar Papers 제목 키워드 기반

Near-Optimal Private Learning in Linear Contextual Bandits

2025-02-18 · Fan Chen, Jiachun Li, Alexander Rakhlin, David Simchi-Levi

We analyze the problem of private learning in generalized linear contextual bandits. Our approach is based on a novel method of re-weighted regression, yielding an efficient algorithm with regret of order $\sqrt{T}+\frac…

Multi-Armed Bandits

Improved Differentially Private Regression via Gradient Boosting

2023-03-06 · Shuai Tang, Sergul Aydore, Michael Kearns, Saeyoung Rho 외

We revisit the problem of differentially private squared error linear regression. We observe that existing state-of-the-art methods are sensitive to the choice of hyperparameters -- including the ``clipping threshold'' t…

regression

(Nearly) Optimal Private Linear Regression via Adaptive Clipping

2022-07-11 · Prateek Varshney, Abhradeep Thakurta, Prateek Jain

We study the problem of differentially private linear regression where each data point is sampled from a fixed sub-Gaussian style distribution. We propose and analyze a one-pass mini-batch stochastic gradient descent met…

regression

Differentially Private Multi-Party Data Release for Linear Regression

2022-06-16 · Ruihan Wu, Xin Yang, Yuanshun Yao, Jiankai Sun 외

Differentially Private (DP) data release is a promising technique to disseminate data without compromising the privacy of data subjects. However the majority of prior work has focused on scenarios where a single party ow…

regression

Private Sketches for Linear Regression

2025-11-10 · Shrutimoy Das, Debanuj Nayak, Anirban Dasgupta arxiv

Linear regression is frequently applied in a variety of domains, some of which might contain sensitive information. This necessitates that the application of these methods does not reveal private information. Differentia…

Computational Efficiency