SOTAVerified

Neural Network Compression

Papers

Showing 5175 of 193 papers

TitleStatusHype
Soft Weight-Sharing for Neural Network CompressionCode0
DeepSZ: A Novel Framework to Compress Deep Neural Networks by Using Error-Bounded Lossy CompressionCode0
Minimal Random Code Learning: Getting Bits Back from Compressed Model ParametersCode0
Differentiable Fine-grained Quantization for Deep Neural Network CompressionCode0
Automatic Neural Network Compression by Sparsity-Quantization Joint Learning: A Constrained Optimization-based ApproachCode0
Dirichlet Pruning for Neural Network CompressionCode0
Additive Tree-Structured Conditional Parameter Spaces in Bayesian Optimization: A Novel Covariance Function and a Fast ImplementationCode0
Characterising Across-Stack Optimisations for Deep Convolutional Neural NetworksCode0
Language Models as Zero-shot Lossless Gradient Compressors: Towards General Neural Parameter Prior ModelsCode0
Magnitude and Similarity based Variable Rate Filter Pruning for Efficient Convolution Neural NetworksCode0
Neural Network Compression of ACAS Xu Early Prototype is Unsafe: Closed-Loop Verification through Quantized State BackreachabilityCode0
Improving Neural Network Quantization without Retraining using Outlier Channel SplittingCode0
Efficient CNN-LSTM based Image Captioning using Neural Network CompressionCode0
A Programmable Approach to Neural Network CompressionCode0
Forward and Backward Information Retention for Accurate Binary Neural NetworksCode0
Focused Quantization for Sparse CNNsCode0
ECC: Platform-Independent Energy-Constrained Deep Neural Network Compression via a Bilinear Regression ModelCode0
Adaptive Distillation: Aggregating Knowledge from Multiple Paths for Efficient DistillationCode0
Heavy Tails in SGD and Compressibility of Overparametrized Neural NetworksCode0
Implicit Compressibility of Overparametrized Neural Networks Trained with Heavy-Tailed SGDCode0
Exact Backpropagation in Binary Weighted Networks with Group Weight TransformationsCode0
Few Sample Knowledge Distillation for Efficient Network CompressionCode0
Joint Matrix Decomposition for Deep Convolutional Neural Networks CompressionCode0
Learning Sparse Networks Using Targeted DropoutCode0
Neural Network Compression Using Higher-Order Statistics and AuxiliaryReconstruction LossesCode0
Show:102550
← PrevPage 3 of 8Next →

No leaderboard results yet.