paper-with-me

Papers

A Knowledge Transfer Framework for Differentially Private Sparse Learning

2019-09-13 · Lingxiao Wang, Quanquan Gu

We study the problem of estimating high dimensional models with underlying sparse structures while preserving the privacy of each training example. We develop a differentially private high-dimensional sparse learning framework using the idea of knowledge transfer. More specifically, we propose to distill the knowledge from a "teacher" estimator trained on a private dataset, by creating a new dataset from auxiliary features, and then train a differentially private "student" estimator using this new dataset. In addition, we establish the linear convergence rate as well as the utility guarantee for our proposed method. For sparse linear regression and sparse logistic regression, our method achieves improved utility guarantees compared with the best known results (Kifer et al., 2012; Wang and Gu, 2019). We further demonstrate the superiority of our framework through both synthetic and real-world data experiments.

📄 PDF Abstract BibTeX arXiv:1909.06322

Code (0)

등록된 구현이 없습니다.

Tasks

regressionSparse LearningTransfer Learning

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

Model-Agnostic Private Learning

2018-12-01 · NeurIPS 2018 12 · Raef Bassily, Abhradeep Guha Thakurta, Om Dipakbhai Thakkar

We design differentially private learning algorithms that are agnostic to the learning model assuming access to limited amount of unlabeled public data. First, we give a new differentially private algorithm for answering…

General ClassificationmodelTransfer Learning

An Optimization Framework for Differentially Private Sparse Fine-Tuning

2025-03-17 · Mehdi Makni, Kayhan Behdin, Gabriel Afriat, Zheng Xu 외

Differentially private stochastic gradient descent (DP-SGD) is broadly considered to be the gold standard for training and fine-tuning neural networks under differential privacy (DP). With the increasing availability of …

Transfer Learning

Quantum Differentially Private Sparse Regression Learning

2020-07-23 · Yuxuan Du, Min-Hsiu Hsieh, Tongliang Liu, Shan You 외

The eligibility of various advanced quantum algorithms will be questioned if they can not guarantee privacy. To fill this knowledge gap, here we devise an efficient quantum differentially private (QDP) Lasso estimator to…

BIG-bench Machine Learningregression

Differentially Private Iterative Screening Rules for Linear Regression

2025-02-25 · Amol Khanna, Fred Lu, Edward Raff

Linear $L_1$-regularized models have remained one of the simplest and most effective tools in data science. Over the past decade, screening rules have risen in popularity as a way to eliminate features when producing the…

Privacy Preservingregression

A Framework for Private Matrix Analysis

2020-09-06 · Jalaj Upadhyay, Sarvagya Upadhyay

We study private matrix analysis in the sliding window model where only the last $W$ updates to matrices are considered useful for analysis. We give first efficient $o(W)$ space differentially private algorithms for spec…