NeurIPS

Quantization

BinGAN: Learning Compact Binary Descriptors with a Regularized GAN
HitNet: Hybrid Ternary Recurrent Neural Network

Pruning

Frequency-Domain Dynamic Pruning for Convolutional Neural Networks
Discrimination-aware Channel Pruning for Deep Neural Networks
ChannelNets: Compact and Efficient Convolutional Neural Networks via Channel-Wise Convolutions

Distillation

Paraphrasing Complex Network: Network Compression via Factor Transfer

ICML

Compression

Compressing Neural Networks using the Variational Information Bottleneck
Weightless: Lossy weight encoding for deep neural network compression

CVPR

Quantization

Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference
SYQ: Learning Symmetric Quantization for Efficient Deep Neural Networks
Two-Step Quantization for Low-Bit Neural Networks
CLIP-Q: Deep Network Compression Learning by In-Parallel Pruning-Quantization
Quantization of Fully Convolutional Networks for Accurate Biomedical Image Segmentation
Explicit Loss-Error-Aware Quantization for Low-Bit Deep Neural Networks

Pruning

PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning
"Learning-Compression" Algorithms for Neural Net Pruning
NISP: Pruning Networks Using Neuron Importance Score Propagation
Learning Compact Recurrent Neural Networks With Block-Term Tensor Decomposition

Low-Rank Approximation

Wide Compression: Tensor Ring Nets

ICLR

Quantization

Loss-aware Weight Quantization of Deep Networks
Alternating Multi-bit Quantization for Recurrent Neural Networks
Adaptive Quantization of Neural Networks
Variational Network Quantization
Model compression via distillation and quantization

Pruning

Stochastic activation pruning for robust adversarial defense
Rethinking the smaller-norm-less-informative assumption in channel pruning of convolution layers
N2N learning: Network to Network Compression via Policy Gradient Reinforcement Learning

System

Espresso: Efficient Forward Propagation for Binary Deep Neural Networks