English
Related papers

Related papers: Implicit Bias in Noisy-SGD: With Applications to D…

200 papers

Training large neural networks with meaningful/usable differential privacy security guarantees is a demanding challenge. In this paper, we tackle this problem by revisiting the two key operations in Differentially Private Stochastic…

Machine Learning · Computer Science 2022-10-11 Hanshen Xiao , Jun Wan , Srinivas Devadas

Differentially Private Stochastic Gradient Descent (DP-SGD) is a key method for applying privacy in the training of deep learning models. It applies isotropic Gaussian noise to gradients during training, which can perturb these gradients in…

Machine Learning · Computer Science 2023-11-28 Pedro Faustini , Natasha Fernandes , Shakila Tonni , Annabelle McIver , Mark Dras

Machine learning models are known to memorize private data to reduce their training loss, which can be inadvertently exploited by privacy attacks such as model inversion and membership inference. To protect against these attacks,…

Machine Learning · Computer Science 2023-11-30 Jie Fu , Qingqing Ye , Haibo Hu , Zhili Chen , Lulu Wang , Kuncan Wang , Xun Ran

Differentially private stochastic gradient descent (DP-SGD) has been instrumental in privately training deep learning models by providing a framework to control and track the privacy loss incurred during training. At the core of this…

Machine Learning · Computer Science 2024-08-21 Jeremiah Birrell , Reza Ebrahimi , Rouzbeh Behnia , Jason Pacheco

Machine learning models trained with \emph{stochastic} gradient descent (SGD) can generalize better than those trained with deterministic gradient descent (GD). In this work, we study SGD's impact on generalization through the lens of the…

Machine Learning · Computer Science 2025-12-09 Hongjian Lan , Yucong Liu , Florian Schäfer

The gradient noise (GN) in the stochastic gradient descent (SGD) algorithm is often considered to be Gaussian in the large data regime by assuming that the classical central limit theorem (CLT) kicks in. This assumption is often made for…

Machine Learning · Computer Science 2019-01-21 Umut Simsekli , Levent Sagun , Mert Gurbuzbalaban

Differentially private stochastic gradient descent (DP-SGD) is the standard algorithm for training machine learning models under differential privacy (DP). The most common DP-SGD privacy accountants rely on Poisson subsampling to ensure the…

Machine Learning · Computer Science 2026-01-14 Sebastian Rodriguez Beltran , Marlon Tobaben , Joonas Jälkö , Niki Loppi , Antti Honkela

Differential privacy (DP) is widely being employed in the industry as a practical standard for privacy protection. While private training of computer vision or natural language processing applications has been studied extensively, the…

Information Retrieval · Computer Science 2024-04-16 Juntaek Lim , Youngeun Kwon , Ranggi Hwang , Kiwan Maeng , G. Edward Suh , Minsoo Rhu

The arguably most widely employed algorithm to train deep neural networks with Differential Privacy is DPSGD, which requires clipping and noising of per-sample gradients. This introduces a reduction in model utility compared to non-private…

Computer Vision and Pattern Recognition · Computer Science 2022-05-10 Nicolas W. Remerscheid , Alexander Ziller , Daniel Rueckert , Georgios Kaissis

The classical statistical learning theory implies that fitting too many parameters leads to overfitting and poor performance. That modern deep neural networks generalize well despite a large number of parameters contradicts this finding and…

Machine Learning · Statistics 2022-10-18 Masaaki Imaizumi , Johannes Schmidt-Hieber

Scalability is a significant challenge when it comes to applying differential privacy to training deep neural networks. The commonly used DP-SGD algorithm struggles to maintain a high level of privacy protection while achieving high…

Computer Vision and Pattern Recognition · Computer Science 2023-06-22 Kamil Adamczewski , Yingchen He , Mijung Park

Graduated optimization is a global optimization technique that is used to minimize a multimodal nonconvex function by smoothing the objective function with noise and gradually refining the solution. This paper experimentally evaluates the…

Machine Learning · Computer Science 2024-12-17 Naoki Sato , Hideaki Iiduka

Differentially Private Stochastic Gradient Descent (DPSGD) is widely utilized to preserve training data privacy in deep learning, which first clips the gradients to a predefined norm and then injects calibrated noise into the training…

Machine Learning · Computer Science 2024-05-29 Haichao Sha , Yang Cao , Yong Liu , Yuncheng Wu , Ruixuan Liu , Hong Chen

Differentially Private Stochastic Gradient Descent (DPSGD) is widely used to train deep neural networks with formal privacy guarantees. However, the addition of differential privacy (DP) often degrades model accuracy by introducing both…

Machine Learning · Computer Science 2025-11-13 Xincheng Xu , Thilina Ranbaduge , Qing Wang , Thierry Rakotoarivelo , David Smith

Training deep neural network is a high dimensional and a highly non-convex optimization problem. Stochastic gradient descent (SGD) algorithm and it's variations are the current state-of-the-art solvers for this task. However, due to…

Machine Learning · Computer Science 2017-01-17 Xi He , Dheevatsa Mudigere , Mikhail Smelyanskiy , Martin Takáč

With rise of machine learning (ML) and the proliferation of smart mobile devices, recent years have witnessed a surge of interest in performing ML in wireless edge networks. In this paper, we consider the problem of jointly improving data…

Distributed, Parallel, and Cluster Computing · Computer Science 2020-03-31 Xin Zhang , Minghong Fang , Jia Liu , Zhengyuan Zhu

For nonconvex objective functions, including those found in training deep neural networks, stochastic gradient descent (SGD) with momentum is said to converge faster and have better generalizability than SGD without momentum. In particular,…

Machine Learning · Computer Science 2025-07-03 Naoki Sato , Hideaki Iiduka

As the use of large embedding models in recommendation systems and language applications increases, concerns over user data privacy have also risen. DP-SGD, a training algorithm that combines differential privacy with stochastic gradient…

Machine Learning · Computer Science 2023-11-15 Badih Ghazi , Yangsibo Huang , Pritish Kamath , Ravi Kumar , Pasin Manurangsi , Amer Sinha , Chiyuan Zhang

Understanding the behavior of stochastic gradient descent (SGD) in the context of deep neural networks has raised lots of concerns recently. Along this line, we study a general form of gradient based optimization dynamics with unbiased…

Machine Learning · Statistics 2019-06-11 Zhanxing Zhu , Jingfeng Wu , Bing Yu , Lei Wu , Jinwen Ma

Differential privacy (DP) has been applied in deep learning for preserving privacy of the underlying training sets. Existing DP practice falls into three categories - objective perturbation, gradient perturbation and output perturbation.…

Cryptography and Security · Computer Science 2022-04-28 Zhigang Lu , Hassan Jameel Asghar , Mohamed Ali Kaafar , Darren Webb , Peter Dickinson