awesome-deep-model-compression

List of papers related to ML and DL model compression for embedded devices(Mobiles, IoT)

Machine Learning

• 2017 Resource-efficient Machine Learning in 2 KB RAM for the Internet of Things

Deep Learning

• Pruning

  • 1993 Second order derivatives for network pruning: Optimal brain surgeon
  • 2001 A simple neural network pruning algorithm with application to filter synthesis
  • 2015 NIPS Learning both weights and connections for efficient neural network
  • 2015 Data-free parameter pruning for deep neural networks
  • 2016 Pruning filters for efficient convnets
  • 2016 Pruning convolutional neural networks for resource efficient transfer learning
  • 2016 Pruning Convolutional Neural Networks for Resource Efficient Inference
  • 2016 A Simple yet Effective Method to Prune Dense Layers of Neural Networks
  • 2017 Structured pruning of deep convolutional neural networks.
  • 2017 Learning Sparse Neural Networks through L0 Regularization
  • 2017 Channel pruning for accelerating very deep neural networks
  • 2017 Runtime neural pruning
  • 2017 Net-trim: Convex pruning of deep neural networks with performance guarantee.
  • 2018 Faster Gaze Prediction With Dense Networks and Fisher Pruning

• Quantization

• Prunig and Quantization

  • 2015 Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding

• Binarization

• Low-Rank-Factorization

• Knowledge Distilation

• Stucture

• Sparse

• Others