On the Compression of Neural Networks Using $\ell_0$-Norm Regularization and Weight Pruning

-norm regularization to avoid overfitting as well as fine tuning to improve the performance of the pruned network. Experimental results are presented aiming to show the effectiveness of the proposed scheme as well as to make comparisons with competing approaches.

cs.LG cs.AI eess.SP Neural Networks and Applications Image and Signal Denoising Methods Advanced Neural Network Applications Computer Science Engineering Medicine

View graph Source

Paper

References (63)

01Exploring the Effect of ℓ0/ℓ2 Regularization in Neural Network Pruning using the LC ToolkitYerlan Idelbayev, Miguel Á. Carreira-Perpiñán2022 · IEEE International Conference on Acoustics, Speech, and Signal Processing · 4 citations

02Pruning and Quantization for Deep Neural Network Acceleration: A SurveyTailin Liang, C. Glossner, Lei Wang et al.2021 · Neurocomputing · 987 citations In Library

03Pruning Deep Neural Networks with $\ell_{0}$-constrained OptimizationD. Phan, Lam M. Nguyen, Nam H. Nguyen et al.2020 · Industrial Conference on Data Mining · 3 citations

04Methods for Pruning Deep Neural NetworksS. Vadera, Salem Ameen2020 · IEEE Access · 194 citations In Library

05Compressing Deep Networks by Neuron Agglomerative ClusteringLina Wang, Wenxue Liu, Xiang Liu et al.2020 · Italian National Conference on Sensors · 6 citations

06DHP: Differentiable Meta Pruning via HyperNetworksYawei Li, Shuhang Gu, K. Zhang et al.2020 · European Conference on Computer Vision · 139 citations In Library

07What is the State of Neural Network Pruning?Davis W. Blalock, J. J. Ortiz, Jonathan Frankle et al.2020 · Conference on Machine Learning and Systems · 1.3k citations In Library

08Structured Compression of Deep Neural Networks with Debiased Elastic Group LASSOO. Oyedotun, D. Aouada, B. Ottersten2020 · IEEE Workshop/Winter Conference on Applications of Computer Vision · 15 citations

09Redundant feature pruning for accelerated inference in deep neural networksB. Ayinde, T. Inanc, J. Zurada2019 · Neural Networks · 104 citations

10Global Sparse Momentum SGD for Pruning Very Deep Neural NetworksXiaohan Ding, Guiguang Ding, Xiangxin Zhou et al.2019 · Neural Information Processing Systems · 193 citations In Library

11Variational Convolutional Neural Network PruningChenglong Zhao, Bingbing Ni, Jian Zhang et al.2019 · Computer Vision and Pattern Recognition · 350 citations

12Compressing Convolutional Neural Networks via Factorized Convolutional FiltersTuanhui Li, Baoyuan Wu, Yujiu Yang et al.2019 · Computer Vision and Pattern Recognition · 107 citations

Scroll for more · 38 remaining

Similar papers

Compressing Convolutional Neural Networks by L0 RegularizationAndrás Formanek, D. Hadhazi2019 · 2019 International Conference on Control, Artificial Intelligence, Robotics & Optimization (ICCAIRO) · 3 citations In Library

L0 Regularization based Fine-grained Neural Network Pruning MethodQixin Xie, Chao Li, Boyu Diao et al.2019 · European Conference on Artificial Intelligence · 4 citations In Library

Exploring the Effect of ℓ<sub>0</sub>/ℓ<sub>2</sub> Regularization in Neural Network Pruning using the LC ToolkitYerlan Idelbayev, Miguel Á. Carreira-Perpiñán2022 · ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · 4 citations In Library

Automated Pruning for Deep Neural Network CompressionFranco Manessi, A. Rozza, S. Bianco et al.2017 · International Conference on Pattern Recognition · 60 citations In Library

Learning Sparse Neural Networks through $L_0$ RegularizationChristos Louizos, M. Welling, Diederik P. Kingma2017 · International Conference on Learning Representations · 1.3k citations In Library

Deep Neural Network Pruning with Progressive RegularizerYexu Zhou, Haibin Zhao, Michael Hefenbrock et al.2024 · IEEE International Joint Conference on Neural Network · 4 citations In Library

Improving Neural Network Efficiency Through Advanced Pruning TechniquesNayeli Tyche, Alex H. Taylor, Jordan Evans et al.2024 In Library

Improving Neural Network Efficiency Through Advanced Pruning TechniquesNayeli Tyche, Alex H. Taylor, Jordan Evans et al.2024 In Library

Regularization-based Pruning of Irrelevant Weights in Deep Neural ArchitecturesGiovanni Bonetta, Matteo Ribero, R. Cancelliere2022 · arXiv (Cornell University) · 10 citations In Library

A unified DNN weight compression framework using reweighted optimization methodsMengchen Fan, Tianyun Zhang, Xiaolong Ma et al.2025 · Intelligent Systems with Applications · 0 citations In Library

Source of record

arXiv

44B

Welcome.

This panel sticks with you. Pick anything below and it opens right beside it, so you can dig through 60,000-plus records without ever losing your spot here.

Travel 44B

LibraryPapers, policy, standards, statute LabsEvery organization building AI ModelsIntelligence, price, and speed BenchmarksThe evaluation catalog IncidentsAI failures and harms SearchOne field across everything DashboardThe state of AI accountability in NY 44B RegistryThe Art. 44-B compliance portal