paper-with-me

Papers

Differentially Private Random Block Coordinate Descent

2024-12-22 · Artavazd Maranjyan, Abdurakhmon Sadiev, Peter Richtárik

Coordinate Descent (CD) methods have gained significant attention in machine learning due to their effectiveness in solving high-dimensional problems and their ability to decompose complex optimization tasks. However, classical CD methods were neither designed nor analyzed with data privacy in mind, a critical concern when handling sensitive information. This has led to the development of differentially private CD methods, such as DP-CD (Differentially Private Coordinate Descent) proposed by Mangold et al. (ICML 2022), yet a disparity remains between non-private CD and DP-CD methods. In our work, we propose a differentially private random block coordinate descent method that selects multiple coordinates with varying probabilities in each iteration using sketch matrices. Our algorithm generalizes both DP-CD and the classical DP-SGD (Differentially Private Stochastic Gradient Descent), while preserving the same utility guarantees. Furthermore, we demonstrate that better utility can be achieved through importance sampling, as our method takes advantage of the heterogeneity in coordinate-wise smoothness constants, leading to improved convergence rates.

📄 PDF Abstract BibTeX arXiv:2412.17054

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음

Similar Papers 제목 키워드 기반

Differentially Private Stochastic Coordinate Descent

2020-06-12 · Georgios Damaskinos, Celestine Mendler-Dünner, Rachid Guerraoui, Nikolaos Papandreou 외

In this paper we tackle the challenge of making the stochastic coordinate descent algorithm differentially private. Compared to the classical gradient descent algorithm where updates operate on a single model vector and …

Differentially Private Coordinate Descent for Composite Empirical Risk Minimization

2021-10-22 · Paul Mangold, Aurélien Bellet, Joseph Salmon, Marc Tommasi

Machine learning models can leak information about the data used to train them. To mitigate this issue, Differentially Private (DP) variants of optimization algorithms like Stochastic Gradient Descent (DP-SGD) have been …

Differentially Private Neural Network Training under Hidden State Assumption

2024-07-11 · Ding Chen, Chen Liu

We present a novel approach called differentially private stochastic block coordinate descent (DP-SBCD) for training neural networks with provable guarantees of differential privacy under the hidden state assumption. Our…

High-Dimensional Private Empirical Risk Minimization by Greedy Coordinate Descent

2022-07-04 · Paul Mangold, Aurélien Bellet, Joseph Salmon, Marc Tommasi

In this paper, we study differentially private empirical risk minimization (DP-ERM). It has been shown that the worst-case utility of DP-ERM reduces polynomially as the dimension increases. This is a major obstacle to pr…

Vocal Bursts Intensity Prediction

When Do Fewer Coordinates Suffice in DP-SGD?

2026-06-03 · Huiqi Zhang, Fang Xie arxiv

Differentially private stochastic gradient descent (DP-SGD) injects noise into every updated coordinate, making the injected noise energy scale with the ambient parameter dimension \(d\). We ask when private training can…