Model Compression

Neural Network Pruning Denoises the Features and Makes Local Connectivity Emerge in Visual Tasks ICML 2022 Neural Parameter Allocation Search ICLR 2022 Non-Uniform Adversarially Robust Pruning AutoML 2022 Nonuniform-to-Uniform Quantization: Towards Accurate Quantization via Generalized Straight-Through Estimation CVPR 2022 On-Device Training Under 256KB Memory NeurIPS 2022 Online Deep Equilibrium Learning for Regularization by Denoising NeurIPS 2022 On the Channel Pruning using Graph Convolution Network for Convolutional Neural Network Acceleration IJCAI 2022 Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning NeurIPS 2022 Optimal Clipping and Magnitude-aware Differentiation for Improved Quantization-aware Training ICML 2022 PALBERT: Teaching ALBERT to Ponder NeurIPS 2022 Parameter-Efficient Sparsity for Large Language Models Fine-Tuning IJCAI 2022 Partially-Random Initialization: A Smoking Gun for Binarization Hypothesis of BERT EMNLP 2022 PATS: Sensitivity-aware Noisy Learning for Pretrained Language Models EMNLP 2022 Pixelated Butterfly: Simple and Efficient Sparse training for Neural Network Models ICLR 2022 Playing Lottery Tickets with Vision and Language AAAI 2022 Plug and Play Knowledge Distillation for kNN-LM with External Logits AACL 2022 Pre-activation Distributions Expose Backdoor Neurons NeurIPS 2022 Probing Structured Pruning on Multilingual Pre-trained Models: Settings, Algorithms, and Efficiency ACL 2022 Proper Reuse of Image Classification Features Improves Object Detection CVPR 2022 Prospect Pruning: Finding Trainable Weights at Initialization using Meta-Gradients ICLR 2022 Provable Defense against Backdoor Policies in Reinforcement Learning NeurIPS 2022 Pruning Adatperfusion with Lottery Ticket Hypothesis NAACL 2022 Pruning-as-Search: Efficient Neural Architecture Search via Channel Pruning and Structural Reparameterization IJCAI 2022 Pruning has a disparate impact on model accuracy NeurIPS 2022 Pruning Neural Networks via Coresets and Convex Geometry: Towards No Assumptions NeurIPS 2022