Model Compression

Two-Step Quantization for Low-Bit Neural Networks CVPR 2018 Variational Network Quantization ICLR 2018 Verifiable Reinforcement Learning via Policy Extraction NeurIPS 2018 Viterbi-based Pruning for Sparse Matrix with Fixed and High Index Compression Ratio ICLR 2018 Weightless: Lossy weight encoding for deep neural network compression ICML 2018 WRPN: Wide Reduced-Precision Networks ICLR 2018 WSNet: Compact and Efficient Networks Through Weight Sampling ICML 2018 Compressed Time Delay Neural Network for Small-Footprint Keyword Spotting Interspeech 2017 Compression-aware Training of Deep Networks NeurIPS 2017 LCNN: Lookup-Based Convolutional Neural Network CVPR 2017 Learning to Prune Deep Neural Networks via Layer-wise Optimal Brain Surgeon NeurIPS 2017 Node Pruning Based on Entropy of Weights and Node Activity for Small-Footprint Acoustic Model Based on Deep Neural Networks Interspeech 2017 On Blackbox Backpropagation and Jacobian Sensing NeurIPS 2017 ProtoNN: Compressed and Accurate kNN for Resource-scarce Devices ICML 2017 Reliably Learning the ReLU in Polynomial Time COLT 2017 Runtime Neural Pruning NeurIPS 2017 Structured Bayesian Pruning via Log-Normal Multiplicative Noise NeurIPS 2017 Training Quantized Nets: A Deeper Understanding NeurIPS 2017 Unfolding and Shrinking Neural Machine Translation Ensembles EMNLP 2017 Variational Dropout Sparsifies Deep Neural Networks ICML 2017 Blockout: Dynamic Model Selection for Hierarchical Deep Networks CVPR 2016 Compressing Bayes Net CPTs with Persistent Leaky Causes PGM 2016 Learning Succinct Models: Pipelined Compression with L1-Regularization, Hashing, Elias-Fano Indices, and Quantization COLING 2016 Model Compression Applied to Small-Footprint Keyword Spotting Interspeech 2016 An Exploration of Parameter Redundancy in Deep Networks With Circulant Projections ICCV 2015