Sensitivity-informed provable pruning of neural networks

DOI10.1137/20M1383239MaRDI QIDQ5037562zbMATH OpenOpenAlexWikidataFDO

Authors Cenk Baykal, Lucas Liebenwein, Igor Gilitschenski, Dan Feldman, Daniela Rus

Publication date 1 March 2022

Published in SIAM Journal on Mathematics of Data Science (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1137/20m1383239

zbMATH Keywords

compressiongeneralizationpruning

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Fast convex pruning of deep neural networks
• Neural Network Pruning with Tukey-Kramer Multiple Comparison Procedure
• A pruning algorithm based on neural complexity
• Make _1 regularization effective in training sparse CNN
• Efficient and sparse neural networks by pruning weights in a multiobjective learning approach

Cites work

• A unified framework for approximating and clustering data
• Deep double descent: where bigger models and more data hurt*
• Fast convex pruning of deep neural networks
• High-dimensional probability. An introduction with applications in data science
• scientific article; zbMATH DE number 2107836 (Why is no real title available?)
• Improved Approximation Guarantees for Packing and Covering Integer Programs
• Multi-task kernel learning based on probabilistic Lipschitzness
• Practical algorithms for a family of waterfilling solutions

Cited in

(12)

• PAC-Bayesian framework based drop-path method for 2D discriminative convolutional network pruning
• Efficient and sparse neural networks by pruning weights in a multiobjective learning approach
• SVD-based DNN pruning and retraining
• Joint structure and parameter optimization of multiobjective sparse neural network
• Fast convex pruning of deep neural networks
• scientific article; zbMATH DE number 7626756 (Why is no real title available?)
• Getting away with more network pruning: from sparsity to geometry and linear regions
• A brain-inspired algorithm for training highly sparse neural networks
• PAC-learning with approximate predictors
• Pruning during training by network efficacy modeling
• Deep Neural Networks Pruning via the Structured Perspective Regularization
• Simultaneous compression and stabilization of neural networks through pruning

Describes a project that uses

Uses Software

• SqueezeNet

This page was built for publication: Sensitivity-informed provable pruning of neural networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5037562)