Neural Network Optimization

Meta Learning in the Continuous Time Limit AISTATS 2021 Meta-learning Symmetries by Reparameterization ICLR 2021 Meta-learning with an Adaptive Task Scheduler NeurIPS 2021 M-FAC: Efficient Matrix-Free Approximations of Second-Order Information NeurIPS 2021 Momentum Centering and Asynchronous Update for Adaptive Gradient Methods NeurIPS 2021 Momentum Residual Neural Networks ICML 2021 MTAdam: Automatic Balancing of Multiple Training Loss Terms EMNLP 2021 Multi-Grained Knowledge Distillation for Named Entity Recognition NAACL 2021 Multi-Scale Selective Feedback Network with Dual Loss for Real Image Denoising IJCAI 2021 NASOA: Towards Faster Task-Oriented Online Fine-Tuning With a Zoo of Models ICCV 2021 NetAdaptV2: Efficient Neural Architecture Search With Fast Super-Network Training and Architecture Optimization CVPR 2021 Network Quantization With Element-Wise Gradient Scaling CVPR 2021 Network-to-Network Regularization: Enforcing Occam's Razor to Improve Generalization NeurIPS 2021 Neural Architecture Search as Sparse Supernet AAAI 2021 Neural Architecture Search of SPD Manifold Networks IJCAI 2021 Neural Architecture Search With Random Labels CVPR 2021 Neural Mechanics: Symmetry and Broken Conservation Laws in Deep Learning Dynamics ICLR 2021 Neural networks with late-phase weights ICLR 2021 Neural Relational Inference with Efficient Message Passing Mechanisms AAAI 2021 Newton Method over Networks is Fast up to the Statistical Precision ICML 2021 Noise and Fluctuation of Finite Learning Rate Stochastic Gradient Descent ICML 2021 Noise Stability Regularization for Improving BERT Fine-tuning NAACL 2021 Noisy Gradient Descent Converges to Flat Minima for Nonconvex Matrix Factorization AISTATS 2021 Non-asymptotic Convergence of Adam-type Reinforcement Learning Algorithms under Markovian Sampling AAAI 2021 Nondeterminism and Instability in Neural Network Optimization ICML 2021