Neural Network Optimization

Extrapolation for Large-batch Training in Deep Learning ICML 2020 Fast and Furious Convergence: Stochastic Second Order Methods under Interpolation AISTATS 2020 Fastened CROWN: Tightened Neural Network Robustness Certificates AAAI 2020 Faster Projection-free Online Learning COLT 2020 Fast Neural Network Adaptation via Parameter Remapping and Architecture Search ICLR 2020 Fast Transformers with Clustered Attention NeurIPS 2020 Filter Grafting for Deep Neural Networks CVPR 2020 Filter Response Normalization Layer: Eliminating Batch Dependence in the Training of Deep Neural Networks CVPR 2020 Finding trainable sparse networks through Neural Tangent Transfer ICML 2020 Finite Depth and Width Corrections to the Neural Tangent Kernel ICLR 2020 Finite Regret and Cycles with Fixed Step-Size via Alternating Gradient Descent-Ascent COLT 2020 Finite Versus Infinite Neural Networks: an Empirical Study NeurIPS 2020 Firefly Neural Architecture Descent: a General Approach for Growing Neural Networks NeurIPS 2020 Fixed-Point Back-Propagation Training CVPR 2020 FOAL: Fast Online Adaptive Learning for Cardiac Motion Estimation CVPR 2020 ForceReader: a BERT-based Interactive Machine Reading Comprehension Model with Attention Separation COLING 2020 Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains NeurIPS 2020 Four Things Everyone Should Know to Improve Batch Normalization ICLR 2020 Fractional Underdamped Langevin Dynamics: Retargeting SGD with Momentum under Heavy-Tailed Gradient Noise ICML 2020 Functional Gradient Boosting for Learning Residual-like Networks with Statistical Guarantees AISTATS 2020 GAIT-prop: A biologically plausible learning rule derived from backpropagation of error NeurIPS 2020 Gap-Aware Mitigation of Gradient Staleness ICLR 2020 Generalization bound of globally optimal non-convex neural network training: Transportation map estimation by infinite dimensional Langevin dynamics NeurIPS 2020 Generalization of Two-layer Neural Networks: An Asymptotic Viewpoint ICLR 2020 Generative Teaching Networks: Accelerating Neural Architecture Search by Learning to Generate Synthetic Training Data ICML 2020