scientific article; zbMATH DE number 7626756
From MaRDI portal
Publication:5053261
Authors: T. Hoefler, Dan Alistarh, Tal Ben-Nun, Nikoli Dryden, Alexandra Peste 
Publication date: 6 December 2022
Full work available at URL: https://arxiv.org/abs/2102.00554
Title of this publication is not available (Why is that?)
Recommendations
- Deep Learning as Sparsity-Enforcing Algorithms
- Consistent Sparse Deep Learning: Theory and Computation
- Efficient and sparse neural networks by pruning weights in a multiobjective learning approach
- Learning sparse deep neural networks with a spike-and-slab prior
- Sparse coding for layered neural networks
- scientific article; zbMATH DE number 1748482
- Sparse deep neural networks using \(L_{1,\infty}\)-weight normalization
- An efficient dilution strategy for constructing sparsely connected neural networks
- Fast convex pruning of deep neural networks
- \(L_{1/2}\) regularization methods for weights sparsification of neural networks
Cites Work
- A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems
- NeST: A Neural Network Synthesis Tool Based on a Grow-and-Prune Paradigm
- GitHub
- Title not available (Why is that?)
- Title not available (Why is that?)
- Model Selection and Estimation in Regression with Grouped Variables
- Sparse inverse covariance estimation with the graphical lasso
- 10.1162/15324430152748236
- Non-negative matrix factorization with sparseness constraints
- Title not available (Why is that?)
- A note on the complexity of \(L _{p }\) minimization
- A topological insight into restricted Boltzmann machines
- Learning theory: stability is sufficient for generalization and necessary and sufficient for consistency of empirical risk minimization
- The dropout learning algorithm
- Title not available (Why is that?)
- Variable selection with neural networks
- Quick and robust feature selection: the strength of energy-efficient sparse training for autoencoders
- Deep vs. shallow networks: an approximation theory perspective
- A tutorial on Fisher information
- Pruning of basis functions in nonlinear approximators
- A simple neural network pruning algorithm with application to filter synthesis
- Neural architecture search: a survey
- An Introduction to Variational Autoencoders
- Blended coarse gradient descent for full quantization of deep neural networks
- Sensitivity-informed provable pruning of neural networks
- Stream Semantic Registers: A Lightweight RISC-V ISA Extension Achieving Full Compute Utilization in Single-Issue Cores
- Title not available (Why is that?)
- Predictive coding approximates backprop along arbitrary computation graphs
- Layer-wise adaptive gradient sparsification for distributed deep learning with convergence guarantees
- Pre-defined Sparsity for Low-Complexity Convolutional Neural Networks
- SqueezeFlow: A Sparse CNN Accelerator Exploiting Concise Convolution Rules
Cited In (15)
- Approximation of functions from korobov spaces by deep convolutional neural networks
- Exploring the impact of post-training rounding in regression models.
- Enhancing deep learning algorithm accuracy and stability using multicriteria optimization: an application to distributed learning with MNIST digits
- A brain-inspired algorithm for training highly sparse neural networks
- Neural network training using \(\ell_1\)-regularization and bi-fidelity data
- Getting away with more network pruning: from sparsity to geometry and linear regions
- On the landscape of one-hidden-layer sparse networks and beyond
- SVD-based DNN pruning and retraining
- Sparse Deep Neural Network for Nonlinear Partial Differential Equations
- Deep Learning as Sparsity-Enforcing Algorithms
- Group projected subspace pursuit for block sparse signal reconstruction: convergence analysis and applications
- Sparse learning model with embedded RIP conditions for turbulence super-resolution reconstruction
- Make \(\ell_1\) regularization effective in training sparse CNN
- Inference, learning and attention mechanisms that exploit and preserve sparsity in CNNs
- Extreme sparsification of physics-augmented neural networks for interpretable model discovery in mechanics
Uses Software
This page was built for publication:
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5053261)
