Model Compression

Model compression via distillation and quantization ICLR 2018 MorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep Networks CVPR 2018 Multi-frame Quantization of LSF Parameters Using a Deep Autoencoder and Pyramid Vector Quantizer Interspeech 2018 N2N learning: Network to Network Compression via Policy Gradient Reinforcement Learning ICLR 2018 NISP: Pruning Networks Using Neuron Importance Score Propagation CVPR 2018 OpenNMT System Description for WNMT 2018: 800 words/sec on a single-core CPU ACL 2018 PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning CVPR 2018 Paraphrasing Complex Network: Network Compression via Factor Transfer NeurIPS 2018 Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations JMLR 2018 Scalable methods for 8-bit training of neural networks NeurIPS 2018 Scaling provable adversarial defenses NeurIPS 2018 SecureNets: Secure Inference of Deep Neural Networks on an Untrusted Cloud ACML 2018 Shift: A Zero FLOP, Zero Parameter Alternative to Spatial Convolutions CVPR 2018 ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices CVPR 2018 Sparse DNNs with Improved Adversarial Robustness NeurIPS 2018 Sparse Persistent RNNs: Squeezing Large Recurrent Networks On-Chip ICLR 2018 Statistical Model Compression for Small-Footprint Natural Language Understanding Interspeech 2018 Structured Factored Inference for Probabilistic Programming AISTATS 2018 SYQ: Learning Symmetric Quantization for Efficient Deep Neural Networks CVPR 2018 Tailoring Neural Architectures for Translating from Morphologically Rich Languages COLING 2018 TAPAS: Tricks to Accelerate (encrypted) Prediction As a Service ICML 2018 TETRIS: TilE-matching the TRemendous Irregular Sparsity NeurIPS 2018 The High-Dimensional Geometry of Binary Neural Networks ICLR 2018 Towards Binary-Valued Gates for Robust LSTM Training ICML 2018 TVM: An Automated End-to-End Optimizing Compiler for Deep Learning OSDI 2018