SOTAVerified

Neural Network Compression

Papers

Showing 101125 of 193 papers

TitleStatusHype
Efficient Micro-Structured Weight Unification and Pruning for Neural Network Compression0
Heavy Tails in SGD and Compressibility of Overparametrized Neural NetworksCode0
Towards Compact CNNs via Collaborative CompressionCode0
Data-Free Knowledge Distillation with Soft Targeted Transfer Set Synthesis0
Neural Network Compression for Noisy Storage Devices0
Scaling Up Exact Neural Network Compression by ReLU StabilityCode0
UMEC: Unified model and embedding compression for efficient recommendation systems0
Sparse matrix products for neural network compression0
Efficient CNN-LSTM based Image Captioning using Neural Network CompressionCode0
Multi-head Knowledge Distillation for Model Compression0
Parallel Blockwise Knowledge Distillation for Deep Neural Network CompressionCode0
torchdistill: A Modular, Configuration-Driven Framework for Knowledge DistillationCode0
Deep convolutional neural network compression via coupled tensor decompositionCode0
Dirichlet Pruning for Neural Network CompressionCode0
Neural Network Compression Via Sparse Optimization0
Noisy Neural Network Compression for Analog Storage Devices0
Additive Tree-Structured Conditional Parameter Spaces in Bayesian Optimization: A Novel Covariance Function and a Fast ImplementationCode0
A Survey on Deep Neural Network Compression: Challenges, Overview, and Solutions0
Transform Quantization for CNN (Convolutional Neural Network) Compression0
Differentiable Joint Pruning and Quantization for Hardware Efficiency0
Hybrid Tensor Decomposition in Neural Network Compression0
Neural gradients are near-lognormal: improved quantized and sparse training0
Neural Network Compression Using Higher-Order Statistics and AuxiliaryReconstruction LossesCode0
Convolutional neural networks compression with low rank and sparse tensor decompositions0
An Overview of Neural Network Compression0
Show:102550
← PrevPage 5 of 8Next →

No leaderboard results yet.