English
Related papers

Related papers: Batch Clipping and Adaptive Layerwise Clipping for…

200 papers

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

Training deep neural networks with Stochastic Gradient Descent, or its variants, requires careful choice of both learning rate and batch size. While smaller batch sizes generally converge in fewer training epochs, larger batch sizes offer…

Machine Learning · Computer Science 2018-02-15 Aditya Devarakonda , Maxim Naumov , Michael Garland

Federated learning seeks to address the issue of isolated data islands by making clients disclose only their local training models. However, it was demonstrated that private information could still be inferred by analyzing local model…

Machine Learning · Computer Science 2022-11-30 Jie Fu , Zhili Chen , Xiao Han

Differential privacy has been proven effective for stochastic gradient descent; however, existing methods often suffer from performance degradation in high-dimensional settings, as the scale of injected noise increases with dimensionality.…

Machine Learning · Computer Science 2025-07-10 Huiqi Zhang , Fang Xie

Differentially private stochastic gradient descent (DP-SGD) is known to have poorer training and test performance on large neural networks, compared to ordinary stochastic gradient descent (SGD). In this paper, we perform a detailed study…

Machine Learning · Computer Science 2023-11-14 Lauren Watson , Eric Gan , Mohan Dantam , Baharan Mirzasoleiman , Rik Sarkar

Large convolutional neural networks (CNN) can be difficult to train in the differentially private (DP) regime, since the optimization algorithms require a computationally expensive operation, known as the per-sample gradient clipping. We…

Machine Learning · Computer Science 2022-12-01 Zhiqi Bu , Jialin Mao , Shiyun Xu

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

Stochastic Gradient Descent (SGD) with gradient clipping is a powerful technique for enabling differentially private optimization. Although prior works extensively investigated clipping with a constant threshold, private training remains…

Machine Learning · Computer Science 2024-12-31 Egor Shulgin , Peter Richtárik

Recent advances have substantially improved the accuracy, memory cost, and training speed of differentially private (DP) deep learning, especially on large vision and language models with millions to billions of parameters. In this work, we…

Machine Learning · Computer Science 2023-10-31 Zhiqi Bu , Ruixuan Liu , Yu-Xiang Wang , Sheng Zha , George Karypis

Existing approaches for training neural networks with user-level differential privacy (e.g., DP Federated Averaging) in federated learning (FL) settings involve bounding the contribution of each user's model update by clipping it to some…

Machine Learning · Computer Science 2022-05-11 Galen Andrew , Om Thakkar , H. Brendan McMahan , Swaroop Ramaswamy

Clipping the gradient is a known approach to improving gradient descent, but requires hand selection of a clipping threshold hyperparameter. We present AutoClip, a simple method for automatically and adaptively choosing a gradient clipping…

Audio and Speech Processing · Electrical Eng. & Systems 2020-07-30 Prem Seetharaman , Gordon Wichern , Bryan Pardo , Jonathan Le Roux

Training Deep Neural Networks (DNNs) with small batches using Stochastic Gradient Descent (SGD) yields superior test performance compared to larger batches. The specific noise structure inherent to SGD is known to be responsible for this…

Machine Learning · Statistics 2024-02-14 Tom Sander , Maxime Sylvestre , Alain Durmus

To reduce the long training time of large deep neural network (DNN) models, distributed synchronous stochastic gradient descent (S-SGD) is commonly used on a cluster of workers. However, the speedup brought by multiple workers is limited by…

Machine Learning · Computer Science 2020-03-03 Shaohuai Shi , Zhenheng Tang , Qiang Wang , Kaiyong Zhao , Xiaowen Chu

While federated learning (FL) and differential privacy (DP) have been extensively studied, their application to automatic speech recognition (ASR) remains largely unexplored due to the challenges in training large transformer models.…

Differentially private (DP) contrastive learning aims to learn general-purpose representations from sensitive data, alleviating the privacy leakage concerns of organizations deploying or sharing embedding models trained on private user…

Cryptography and Security · Computer Science 2026-04-30 Kecen Li , Chen Gong , Zinan Lin , Tianhao Wang , Xiaokui Xiao

Differentially private stochastic gradient descent (DP-SGD) is the most widely used method for training machine learning models with provable privacy guarantees. A key challenge in DP-SGD is setting the per-sample gradient clipping…

Machine Learning · Computer Science 2025-10-29 Atefeh Gilani , Naima Tasnim , Lalitha Sankar , Oliver Kosut

We design a new adaptive learning algorithm for misclassification cost problems that attempt to reduce the cost of misclassified instances derived from the consequences of various errors. Our algorithm (adaptive cost sensitive learning -…

Machine Learning · Computer Science 2021-11-16 Ohad Volk , Gonen Singer

A common way to speed up training of large convolutional networks is to add computational units. Training is then performed using data-parallel synchronous Stochastic Gradient Descent (SGD) with mini-batch divided between computational…

Computer Vision and Pattern Recognition · Computer Science 2017-09-15 Yang You , Igor Gitman , Boris Ginsburg

Training neural networks with large batch is of fundamental significance to deep learning. Large batch training remarkably reduces the amount of training time but has difficulties in maintaining accuracy. Recent works have put forward…

Machine Learning · Computer Science 2020-11-30 Jeffrey Fong , Siwei Chen , Kaiqi Chen

While stochastic gradient descent (SGD) is still the \emph{de facto} algorithm in deep learning, adaptive methods like Clipped SGD/Adam have been observed to outperform SGD across important tasks, such as attention models. The settings…

Optimization and Control · Mathematics 2020-10-26 Jingzhao Zhang , Sai Praneeth Karimireddy , Andreas Veit , Seungyeon Kim , Sashank J Reddi , Sanjiv Kumar , Suvrit Sra