Neural Network Optimization

Global Convergence of Deep Networks with One Wide Layer Followed by Pyramidal Topology NeurIPS 2020 Going Deeper With Lean Point Networks CVPR 2020 Gradient ℓ_1 Regularization for Quantization Robustness ICLR 2020 Gradient-based Analysis of NLP Models is Manipulable EMNLP 2020 Gradient descent follows the regularization path for general losses COLT 2020 Gradient Descent with Early Stopping is Provably Robust to Label Noise for Overparameterized Neural Networks AISTATS 2020 Gradients as Features for Deep Representation Learning ICLR 2020 Graph Convolutional Network for Recommendation with Low-pass Collaborative Filters ICML 2020 Growing Adaptive Multi-hyperplane Machines ICML 2020 Hasyarasa at SemEval-2020 Task 7: Quantifying Humor as Departure from Expectedness SemEval 2020 HDK: Toward High-Performance Deep-Learning-Based Kirchhoff Analysis AAAI 2020 Hit-Detector: Hierarchical Trinity Architecture Search for Object Detection CVPR 2020 How Does Noise Help Robustness? Explanation and Exploration under the Neural SDE Framework CVPR 2020 How does Weight Correlation Affect Generalisation Ability of Deep Neural Networks? NeurIPS 2020 Hyperbolic Interaction Model for Hierarchical Multi-Label Classification AAAI 2020 Implicit Bias in Deep Linear Classification: Initialization Scale vs Training Accuracy NeurIPS 2020 Implicit Bias of Gradient Descent for Wide Two-layer Neural Networks Trained with the Logistic Loss COLT 2020 Implicit regularization for deep neural networks driven by an Ornstein-Uhlenbeck like process COLT 2020 Implicit Regularization in Deep Learning May Not Be Explainable by Norms NeurIPS 2020 Improved Analysis of Clipping Algorithms for Non-convex Optimization NeurIPS 2020 Improved memory in recurrent neural networks with sequential non-normal dynamics ICLR 2020 Improved Training Strategies for End-to-End Speech Recognition in Digital Voice Assistants Interspeech 2020 Improving First-Order Optimization Algorithms (Student Abstract) AAAI 2020 Improving Neural Network Training in Low Dimensional Random Bases NeurIPS 2020 Improving the Gating Mechanism of Recurrent Neural Networks ICML 2020