English
Related papers

Related papers: Differentially private training of residual networ…

200 papers

Traditional Differentially Private Stochastic Gradient Descent (DP-SGD) introduces statistical noise on top of gradients drawn from a Gaussian distribution to ensure privacy. This paper introduces the novel Differentially Private Block-wise…

Machine Learning · Computer Science 2025-01-22 David Zagardo

In this paper, we propose a generic and simple strategy for utilizing stochastic gradient information in optimization. The technique essentially contains two consecutive steps in each iteration: 1) computing and normalizing each block…

Machine Learning · Computer Science 2018-04-24 Adams Wei Yu , Lei Huang , Qihang Lin , Ruslan Salakhutdinov , Jaime Carbonell

Massive data exist among user local platforms that usually cannot support deep neural network (DNN) training due to computation and storage resource constraints. Cloud-based training schemes provide beneficial services but suffer from…

Machine Learning · Computer Science 2018-01-15 Meng Li , Liangzhen Lai , Naveen Suda , Vikas Chandra , David Z. Pan

When optimizing over-parameterized models, such as deep neural networks, a large set of parameters can achieve zero training error. In such cases, the choice of the optimization algorithm and its respective hyper-parameters introduces…

Machine Learning · Computer Science 2019-12-06 Gauthier Gidel , Francis Bach , Simon Lacoste-Julien

In this article, we take one step toward understanding the learning behavior of deep residual networks, and supporting the observation that deep residual networks behave like ensembles. We propose a new convolutional neural network…

Computer Vision and Pattern Recognition · Computer Science 2024-10-30 Masoud Abdi , Saeid Nahavandi

This paper focuses on the problem of Differentially Private Stochastic Optimization for (multi-layer) fully connected neural networks with a single output node. In the first part, we examine cases with no hidden nodes, specifically focusing…

Machine Learning · Computer Science 2023-10-13 Hanpu Shen , Cheng-Long Wang , Zihang Xiang , Yiming Ying , Di Wang

The spherical noise added to gradients in differentially private (DP) training undermines the performance of adaptive optimizers like AdaGrad and Adam, and hence many recent works have proposed algorithms to address this challenge. However,…

Machine Learning · Computer Science 2025-07-03 Arun Ganesh , Brendan McMahan , Abhradeep Thakurta

Deep anomaly detection is a difficult task since, in high dimensions, it is hard to completely characterize a notion of "differentness" when given only examples of normality. In this paper we propose a novel approach to deep anomaly…

Machine Learning · Computer Science 2020-10-07 Lucas Deecke , Lukas Ruff , Robert A. Vandermeulen , Hakan Bilen

Fine-tuning large language models on downstream tasks is crucial for realizing their cross-domain potential but often relies on sensitive data, raising privacy concerns. Differential privacy (DP) offers rigorous privacy guarantees and has…

Machine Learning · Computer Science 2026-01-19 Lele Zheng , Xiang Wang , Tao Zhang , Yang Cao , Ke Cheng , Yulong Shen

Distributed online learning has been proven extremely effective in solving large-scale machine learning problems over streaming data. However, information sharing between learners in distributed learning also raises concerns about the…

Machine Learning · Computer Science 2023-10-31 Ziqin Chen , Yongqiang Wang

Learning often involves sensitive data and as such, privacy preserving extensions to Stochastic Gradient Descent (SGD) and other machine learning algorithms have been developed using the definitions of Differential Privacy (DP). In…

Machine Learning · Computer Science 2021-10-14 Friedrich Dörmann , Osvald Frisk , Lars Nørvang Andersen , Christian Fischer Pedersen

Differentially private stochastic gradient descent (DP-SGD) has been widely adopted in deep learning to provide rigorously defined privacy, which requires gradient clipping to bound the maximum norm of individual gradients and additive…

Machine Learning · Computer Science 2023-06-29 Junyi Zhu , Matthew B. Blaschko

We introduce AdaMix, an adaptive differentially private algorithm for training deep neural network classifiers using both private and public image data. While pre-training language models on large public datasets has enabled strong…

Computer Vision and Pattern Recognition · Computer Science 2022-03-30 Aditya Golatkar , Alessandro Achille , Yu-Xiang Wang , Aaron Roth , Michael Kearns , Stefano Soatto

Machine learning with formal privacy-preserving techniques like Differential Privacy (DP) allows one to derive valuable insights from sensitive medical imaging data while promising to protect patient privacy, but it usually comes at a sharp…

Image and Video Processing · Electrical Eng. & Systems 2023-06-21 Florian A. Hölzl , Daniel Rueckert , Georgios Kaissis

Motivated by growing concerns over ensuring privacy on social networks, we develop new algorithms and impossibility results for fitting complex statistical models to network data subject to rigorous privacy guarantees. We consider the…

Statistics Theory · Mathematics 2018-10-05 Christian Borgs , Jennifer Chayes , Adam Smith , Ilias Zadik

Gradient-based methods for the distributed training of residual networks (ResNets) typically require a forward pass of the input data, followed by back-propagating the error gradient to update model parameters, which becomes time-consuming…

Machine Learning · Computer Science 2021-12-13 Qi Sun , Hexin Dong , Zewei Chen , Jiacheng Sun , Zhenguo Li , Bin Dong

Deep learning with differential privacy (DP) has garnered significant attention over the past years, leading to the development of numerous methods aimed at enhancing model accuracy and training efficiency. This paper delves into the…

Machine Learning · Computer Science 2024-08-27 Youlong Ding , Xueyang Wu , Yining Meng , Yonggang Luo , Hao Wang , Weike Pan

We address the challenge of sample efficiency in differentially private fine-tuning of large language models (LLMs) using DP-SGD. While DP-SGD provides strong privacy guarantees, the added noise significantly increases the entropy of…

Machine Learning · Computer Science 2026-01-12 Ali Dadsetan , Frank Rudzicz

This paper proposes a differentially private gradient-tracking-based distributed stochastic optimization algorithm over directed graphs. In particular, privacy noises are incorporated into each agent's state and tracking variable to…

Systems and Control · Electrical Eng. & Systems 2026-04-15 Jialong Chen , Jimin Wang , Ji-Feng Zhang

We present backpropagation clipping, a novel variant of differentially private stochastic gradient descent (DP-SGD) for privacy-preserving deep learning. Our approach clips each trainable layer's inputs (during the forward pass) and its…

Machine Learning · Computer Science 2022-02-21 Timothy Stevens , Ivoline C. Ngong , David Darais , Calvin Hirsch , David Slater , Joseph P. Near
‹ Prev 1 3 4 5 6 7 10 Next ›