Neural Network Optimization

Exploring Discourse Structures for Argument Impact Classification ACL 2021 Exponentially Many Local Minima in Quantum Neural Networks ICML 2021 Extreme Memorization via Scale of Initialization ICLR 2021 Fantastic Four: Differentiable and Efficient Bounds on Singular Values of Convolution Layers ICLR 2021 Fast Certified Robust Training with Short Warmup NeurIPS 2021 Faster Depth-Adaptive Transformers AAAI 2021 Faster Directional Convergence of Linear Neural Networks under Spherically Symmetric Data NeurIPS 2021 Faster Meta Update Strategy for Noise-Robust Deep Learning CVPR 2021 Faster Neural Network Training with Approximate Tensor Operations NeurIPS 2021 Fast Extra Gradient Methods for Smooth Structured Nonconvex-Nonconcave Minimax Problems NeurIPS 2021 Fast Fourier Intrinsic Network WACV 2021 Fast margin maximization via dual acceleration ICML 2021 Few-Shot Neural Architecture Search ICML 2021 Finite-time theory for momentum Q-learning UAI 2021 Flattening Sharpness for Dynamic Gradient Projection Memory Benefits Continual Learning NeurIPS 2021 FP-NAS: Fast Probabilistic Neural Architecture Search CVPR 2021 Fractal Structure and Generalization Properties of Stochastic Optimization Algorithms NeurIPS 2021 Fractional moment-preserving initialization schemes for training deep neural networks AISTATS 2021 Frivolous Units: Wider Networks Are Not Really That Wide AAAI 2021 Functional Regularization for Reinforcement Learning via Learned Fourier Features NeurIPS 2021 GAML-BERT: Improving BERT Early Exiting by Gradient Aligned Mutual Learning EMNLP 2021 Gated Linear Networks AAAI 2021 Gated Transformer for Robust De-noised Sequence-to-Sequence Modelling EMNLP 2021 GDP: Stabilized Neural Network Pruning via Gates With Differentiable Polarization ICCV 2021 Generalization error bounds for deep unfolding RNNs UAI 2021