Model Compression

Similarity Preserving Deep Asymmetric Quantization for Image Retrieval AAAI 2019 Simple, Scalable Adaptation for Neural Machine Translation EMNLP 2019 Simultaneously Optimizing Weight and Quantizer of Ternary Neural Network Using Truncated Gaussian Approximation CVPR 2019 Structured Pruning of Neural Networks With Budget-Aware Regularization CVPR 2019 TAPAS: Train-Less Accuracy Predictor for Architecture Search AAAI 2019 Towards a Theoretical Understanding of Hashing-Based Neural Nets AISTATS 2019 Unifying Heterogeneous Classifiers With Distillation CVPR 2019 Adversarial Distillation of Bayesian Neural Network Posteriors ICML 2018 Approximation Algorithms for Cascading Prediction Models ICML 2018 Binarized LSTM Language Model NAACL 2018 BlockDrop: Dynamic Inference Paths in Residual Networks CVPR 2018 Boosting Combinatorial Problem Modeling with Machine Learning IJCAI 2018 CLIP-Q: Deep Network Compression Learning by In-Parallel Pruning-Quantization CVPR 2018 Compact Personalized Models for Neural Machine Translation EMNLP 2018 Compare, Compress and Propagate: Enhancing Neural Architectures with Alignment Factorization for Natural Language Inference EMNLP 2018 Cuckoo Feature Hashing: Dynamic Weight Sharing for Sparse Analytics IJCAI 2018 DCFNet: Deep Neural Network with Decomposed Convolutional Filters ICML 2018 Deep k-Means: Re-Training and Parameter Sharing with Harder Cluster Assignments for Compressing Deep Convolutions ICML 2018 Efficient Contextualized Representation: Language Model Pruning for Sequence Labeling EMNLP 2018 Efficient Sequence Learning with Group Recurrent Networks NAACL 2018 Explicit Loss-Error-Aware Quantization for Low-Bit Deep Neural Networks CVPR 2018 Frequency-Domain Dynamic Pruning for Convolutional Neural Networks NeurIPS 2018 GradiVeQ: Vector Quantization for Bandwidth-Efficient Gradient Aggregation in Distributed CNN Training NeurIPS 2018 GroupReduce: Block-Wise Low-Rank Approximation for Neural Language Model Shrinking NeurIPS 2018 Heterogeneous Bitwidth Binarization in Convolutional Neural Networks NeurIPS 2018