Neural Network Optimization

The Lottery Ticket Hypothesis for Pre-trained BERT Networks NeurIPS 2020 Theory-Inspired Path-Regularized Differential Network Architecture Search NeurIPS 2020 The phase diagram of approximation rates for deep neural networks NeurIPS 2020 The Pitfalls of Simplicity Bias in Neural Networks NeurIPS 2020 The Statistical Complexity of Early-Stopped Mirror Descent NeurIPS 2020 The Surprising Simplicity of the Early-Time Learning Dynamics of Neural Networks NeurIPS 2020 The Transference Architecture for Automatic Post-Editing COLING 2020 The Usual Suspects? Reassessing Blame for VAE Posterior Collapse ICML 2020 Time-Aware Transformer-based Network for Clinical Notes Series Prediction MLHC 2020 TKD: Temporal Knowledge Distillation for Active Perception WACV 2020 Top-KAST: Top-K Always Sparse Training NeurIPS 2020 Towards Adaptive Residual Network Training: A Neural-ODE Perspective ICML 2020 Towards a General Theory of Infinite-Width Limits of Neural Classifiers ICML 2020 Towards Better Forecasting by Fusing Near and Distant Future Visions AAAI 2020 Towards Better Generalization of Adaptive Gradient Methods NeurIPS 2020 Towards Real-Time DNN Inference on Mobile Platforms with Model Pruning and Compiler Optimization IJCAI 2020 Towards Stable and Efficient Training of Verifiably Robust Neural Networks ICLR 2020 Towards Stream Translation: Adaptive Computation Time for Simultaneous Machine Translation ACL 2020 Towards Theoretically Understanding Why Sgd Generalizes Better Than Adam in Deep Learning NeurIPS 2020 Towards Understanding the Dynamics of the First-Order Adversaries ICML 2020 Training Linear Finite-State Machines NeurIPS 2020 Training Linear Neural Networks: Non-Local Convergence and Complexity Results ICML 2020 Training Neural Networks for and by Interpolation ICML 2020 Training Quantized Neural Networks With a Full-Precision Auxiliary Module CVPR 2020 Training Recurrent Neural Networks Online by Learning Explicit State Variables ICLR 2020