Neural Network Optimization

EC-DARTS: Inducing Equalized and Consistent Optimization Into DARTS ICCV 2021 Edit Distance Based Curriculum Learning for Paraphrase Generation ACL 2021 Editing Factual Knowledge in Language Models EMNLP 2021 Effective Sparsification of Neural Networks With Global Sparsity Constraint CVPR 2021 Effects of Parameter Norm Growth During Transformer Training: Inductive Bias from Gradient Descent EMNLP 2021 Efficient and Accurate Gradients for Neural SDEs NeurIPS 2021 Efficient Differentiable Simulation of Articulated Bodies ICML 2021 Efficient Neural Network Training via Forward and Backward Propagation Sparsification NeurIPS 2021 EfficientSing: A Chinese Singing Voice Synthesis System Using Duration-Free Acoustic Model and HiFi-GAN Vocoder Interspeech 2021 Embedding Principle of Loss Landscape of Deep Neural Networks NeurIPS 2021 Empirical Analysis of Generalized Iterative Speech Separation Networks Interspeech 2021 Empirical Evaluation of Pre-trained Transformers for Human-Level NLP: The Role of Sample Size and Dimensionality NAACL 2021 Empowering Adaptive Early-Exit Inference with Latency Awareness AAAI 2021 Enabling Retrain-free Deep Neural Network Pruning Using Surrogate Lagrangian Relaxation IJCAI 2021 Enhance Curvature Information by Structured Stochastic Quasi-Newton Methods CVPR 2021 Enlivening Redundant Heads in Multi-head Self-attention for Machine Translation EMNLP 2021 Entropic gradient descent algorithms and wide flat minima ICLR 2021 ERNIE-Doc: A Retrospective Long-Document Modeling Transformer ACL 2021 Error Compensated Distributed SGD Can Be Accelerated NeurIPS 2021 ErrorCompensatedX: error compensation for variance reduced algorithms NeurIPS 2021 Evaluating Neural Model Robustness for Machine Comprehension EACL 2021 Evaluating the Extrapolation Capabilities of Neural Vocoders to Extreme Pitch Values Interspeech 2021 Evolving Search Space for Neural Architecture Search ICCV 2021 Explicit loss asymptotics in the gradient descent training of neural networks NeurIPS 2021 Exploiting Local Convergence of Quasi-Newton Methods Globally: Adaptive Sample Size Approach NeurIPS 2021