Efficient Computing

TopicBERT for Energy Efficient Document Classification EMNLP 2020 Top-KAST: Top-K Always Sparse Training NeurIPS 2020 Towards Accurate Low Bit-Width Quantization with Multiple Phase Adaptations AAAI 2020 Towards Accurate Post-training Network Quantization via Bit-Split and Stitching ICML 2020 Towards Certificated Model Robustness Against Weight Perturbations AAAI 2020 Towards Efficient Model Compression via Learned Global Ranking CVPR 2020 Towards Fully 8-bit Integer Inference for the Transformer Model IJCAI 2020 Towards Real-Time DNN Inference on Mobile Platforms with Model Pruning and Compiler Optimization IJCAI 2020 Towards Stabilizing Batch Statistics in Backward Propagation of Batch Normalization ICLR 2020 Towards the Systematic Reporting of the Energy and Carbon Footprints of Machine Learning JMLR 2020 Towards Unified INT8 Training for Convolutional Neural Network CVPR 2020 Train Big, Then Compress: Rethinking Model Size for Efficient Training and Inference of Transformers ICML 2020 Training Decision Trees as Replacement for Convolution Layers AAAI 2020 Training Quantized Neural Networks With a Full-Precision Auxiliary Module CVPR 2020 Training-Time-Friendly Network for Real-Time Object Detection AAAI 2020 Transferable Graph Optimizers for ML Compilers NeurIPS 2020 Transition-based Parsing with Stack-Transformers EMNLP 2020 Triple Wins: Boosting Accuracy, Robustness and Efficiency Together by Enabling Input-Adaptive Inference ICLR 2020 Tuning-free Plug-and-Play Proximal Algorithm for Inverse Imaging Problems ICML 2020 ULSAM: Ultra-Lightweight Subspace Attention Module for Compact Convolutional Neural Networks WACV 2020 Ultrafast Photorealistic Style Transfer via Neural Architecture Search AAAI 2020 Ultra-Low Precision 4-bit Training of Deep Neural Networks NeurIPS 2020 UNAS: Differentiable Architecture Search Meets Reinforcement Learning CVPR 2020 Unconditional Coresets for Regularized Loss Minimization AISTATS 2020 Understanding and Exploring the Network with Stochastic Architectures NeurIPS 2020