Model Compression

Learning Low-precision Neural Networks without Straight-Through Estimator (STE) IJCAI 2019 Learning Recurrent Binary/Ternary Weights ICLR 2019 Learning to Quantize Deep Networks by Optimizing Quantization Intervals With Task Loss CVPR 2019 MetaQuant: Learning to Quantize by Learning to Penetrate Non-differentiable Quantization NeurIPS 2019 Minimal Random Code Learning: Getting Bits Back from Compressed Model Parameters ICLR 2019 Model Compression with Adversarial Robustness: A Unified Optimization Framework NeurIPS 2019 Network Pruning via Transformable Architecture Search NeurIPS 2019 Normalization Helps Training of Quantized LSTM NeurIPS 2019 OICSR: Out-In-Channel Sparsity Regularization for Compact Deep Neural Networks CVPR 2019 One ticket to win them all: generalizing lottery ticket initializations across datasets and optimizers NeurIPS 2019 On Knowledge distillation from complex networks for response prediction NAACL 2019 Online Embedding Compression for Text Classification Using Low Rank Matrix Factorization AAAI 2019 On the Downstream Performance of Compressed Word Embeddings NeurIPS 2019 Parallel Iterative Edit Models for Local Sequence Transduction EMNLP 2019 Partial Order Pruning: For Best Speed/Accuracy Trade-Off in Neural Architecture Search CVPR 2019 Patient Knowledge Distillation for BERT Model Compression EMNLP 2019 Per-Tensor Fixed-Point Quantization of the Back-Propagation Algorithm ICLR 2019 Play and Prune: Adaptive Filter Pruning for Deep Model Compression IJCAI 2019 Private Model Compression via Knowledge Distillation AAAI 2019 Probability Distillation: A Caveat and Alternatives UAI 2019 ProxQuant: Quantized Neural Networks via Proximal Operators ICLR 2019 ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware ICLR 2019 Random Search and Reproducibility for Neural Architecture Search UAI 2019 Rate Distortion For Model Compression:From Theory To Practice ICML 2019 Relaxed Quantization for Discretized Neural Networks ICLR 2019