Model Compression

Clipper: A Low-Latency Online Prediction Serving System NSDI 2017 Compression-aware Training of Deep Networks NeurIPS 2017 Deep Learning With Low Precision by Half-Wave Gaussian Quantization CVPR 2017 Deep Roots: Improving CNN Efficiency With Hierarchical Filter Groups CVPR 2017 Designing Energy-Efficient Convolutional Neural Networks Using Energy-Aware Pruning CVPR 2017 ECO: Efficient Convolution Operators for Tracking CVPR 2017 Fixed-Point Factorized Networks CVPR 2017 Hash Embeddings for Efficient Word Representations NeurIPS 2017 Learning to Prune Deep Neural Networks via Layer-wise Optimal Brain Surgeon NeurIPS 2017 Low-Rank Bilinear Pooling for Fine-Grained Classification CVPR 2017 More Is Less: A More Complicated Network With Less Inference Complexity CVPR 2017 Net-Trim: Convex Pruning of Deep Neural Networks with Performance Guarantee NeurIPS 2017 Network Sketching: Exploiting Binary Structure in Deep CNNs CVPR 2017 Node Pruning Based on Entropy of Weights and Node Activity for Small-Footprint Acoustic Model Based on Deep Neural Networks Interspeech 2017 On Compressing Deep Models by Low Rank and Sparse Decomposition CVPR 2017 Reducing the Computational Complexity of Two-Dimensional LSTMs Interspeech 2017 Runtime Neural Pruning NeurIPS 2017 SplitNet: Learning to Semantically Split Deep Networks for Parameter Reduction and Model Parallelization ICML 2017 Structured Bayesian Pruning via Log-Normal Multiplicative Noise NeurIPS 2017 SVD-Softmax: Fast Softmax Approximation on Large Vocabulary Neural Networks NeurIPS 2017 Towards Accurate Binary Convolutional Neural Network NeurIPS 2017 Towards Compact and Fast Neural Machine Translation Using a Combined Method EMNLP 2017 Unfolding and Shrinking Neural Machine Translation Ensembles EMNLP 2017 Weighted-Entropy-Based Quantization for Deep Neural Networks CVPR 2017 CNNpack: Packing Convolutional Neural Networks in the Frequency Domain NeurIPS 2016