English
Related papers

Related papers: SmoothNets: Optimizing CNN architecture design for…

200 papers

This paper attempts to answer the question whether neural network pruning can be used as a tool to achieve differential privacy without losing much data utility. As a first step towards understanding the relationship between neural network…

Machine Learning · Computer Science 2020-03-05 Yangsibo Huang , Yushan Su , Sachin Ravi , Zhao Song , Sanjeev Arora , Kai Li

The combination of deep neural networks and Differential Privacy has been of increasing interest in recent years, as it offers important data protection guarantees to the individuals of the training datasets used. However, using…

Machine Learning · Computer Science 2021-06-03 Osvald Frisk , Friedrich Dörmann , Christian Marius Lillelund , Christian Fischer Pedersen

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

Deep learning models are often trained on datasets that contain sensitive information such as individuals' shopping transactions, personal contacts, and medical records. An increasingly important line of work therefore has sought to train…

Machine Learning · Computer Science 2020-07-23 Zhiqi Bu , Jinshuo Dong , Qi Long , Weijie J. Su

In this paper, we propose Selective Output Smoothing Regularization, a novel regularization method for training the Convolutional Neural Networks (CNNs). Inspired by the diverse effects on training from different samples, Selective Output…

Computer Vision and Pattern Recognition · Computer Science 2022-03-30 Xuan Cheng , Tianshu Xie , Xiaomin Wang , Qifeng Weng , Minghui Liu , Jiali Deng , Ming Liu

High demand for computation resources severely hinders deployment of large-scale Deep Neural Networks (DNN) in resource constrained devices. In this work, we propose a Structured Sparsity Learning (SSL) method to regularize the structures…

Neural and Evolutionary Computing · Computer Science 2016-10-19 Wei Wen , Chunpeng Wu , Yandan Wang , Yiran Chen , Hai Li

Training time on large datasets for deep neural networks is the principal workflow bottleneck in a number of important applications of deep learning, such as object classification and detection in automatic driver assistance systems (ADAS).…

Machine Learning · Computer Science 2016-11-15 Peter H. Jin , Qiaochu Yuan , Forrest Iandola , Kurt Keutzer

We explore the potential for using a nonsmooth loss function based on the max-norm in the training of an artificial neural network. We hypothesise that this may lead to superior classification results in some special cases where the…

Machine Learning · Computer Science 2021-07-20 Vinesha Peiris , Nadezda Sukhorukova , Vera Roshchina

Road scene understanding is a critical component in an autonomous driving system. Although the deep learning-based road scene segmentation can achieve very high accuracy, its complexity is also very high for developing real-time…

Computer Vision and Pattern Recognition · Computer Science 2019-04-11 Ping-Rong Chen , Hsueh-Ming Hang , Sheng-Wei Chan , Jing-Jhih Lin

Machine learning (ML) models memorize and leak training data, causing serious privacy issues to data owners. Training algorithms with differential privacy (DP), such as DP-SGD, have been gaining attention as a solution. However, DP-SGD adds…

Hardware Architecture · Computer Science 2025-10-09 Donghwan Kim , Xin Gu , Jinho Baek , Timothy Lo , Younghoon Min , Kwangsik Shin , Jongryool Kim , Jongse Park , Kiwan Maeng

Differentially private SGD (DPSGD) has recently shown promise in deep learning. However, compared to non-private SGD, the DPSGD algorithm places computational overheads that can undo the benefit of batching in GPUs. Micro-batching is a…

Machine Learning · Computer Science 2022-06-06 Edward H. Lee , Mario Michael Krell , Alexander Tsyplikhin , Victoria Rege , Errol Colak , Kristen W. Yeom

To meet the demand for designing efficient neural networks with appropriate trade-offs between model performance (e.g., classification accuracy) and computational complexity, the differentiable neural architecture distillation (DNAD)…

Machine Learning · Computer Science 2025-04-30 Xuan Rao , Bo Zhao , Derong Liu

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

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 controlled noise…

Machine Learning · Computer Science 2021-03-16 Georgios Damaskinos , Celestine Mendler-Dünner , Rachid Guerraoui , Nikolaos Papandreou , Thomas Parnell

Differential privacy (DP) provides strong protection for sensitive data, but often reduces model performance and fairness, especially for underrepresented groups. One major reason is gradient clipping in DP-SGD, which can disproportionately…

Machine Learning · Computer Science 2025-10-08 Dorsa Soleymani , Ali Dadsetan , Frank Rudzicz

Differential Privacy (DP) is becoming central to large-scale training as privacy regulations tighten. We revisit how DP noise interacts with adaptivity in optimization through the lens of stochastic differential equations, providing the…

The ability to design complex neural network architectures which enable effective training by stochastic gradient descent has been the key for many achievements in the field of deep learning. However, developing such architectures remains a…

Neural and Evolutionary Computing · Computer Science 2019-07-04 Marcus Märtens , Dario Izzo

Federated learning enables training machine learning models while preserving the privacy of participants. Surprisingly, there is no differentially private distributed method for smooth, non-convex optimization problems. The reason is that…

Machine Learning · Computer Science 2025-02-20 Egor Shulgin , Sarit Khirirat , Peter Richtárik

Federated learning aims to protect data privacy by collaboratively learning a model without sharing private data among users. However, an adversary may still be able to infer the private training data by attacking the released model.…

Machine Learning · Computer Science 2021-09-13 Zhicong Liang , Bao Wang , Quanquan Gu , Stanley Osher , Yuan Yao

Deep neural networks (DNNs) have provided brilliant performance across various tasks. However, this success often comes at the cost of unnecessarily large model sizes, high computational demands, and substantial memory footprints.…

Machine Learning · Computer Science 2025-11-26 Shaharyar Ahmed Khan Tareen , Filza Khan Tareen