Generalization

Implicit regularization for deep neural networks driven by an Ornstein-Uhlenbeck like process COLT 2020 In search of robust measures of generalization NeurIPS 2020 On the Multiple Descent of Minimum-Norm Interpolants and Restricted Lower Isometry of Kernels COLT 2020 Polylogarithmic width suffices for gradient descent to achieve arbitrarily small test error with shallow ReLU networks ICLR 2020 Understanding Architectures Learnt by Cell-based Neural Architecture Search ICLR 2020 Understanding Generalization in Neural Networks for Robustness against Adversarial Vulnerabilities AAAI 2020 Gradient descent aligns the layers of deep linear networks ICLR 2019 ResNet and Batch-normalization Improve Data Separability ACML 2019 Understanding Data Augmentation in Neural Machine Translation: Two Perspectives towards Generalization EMNLP 2019 NAIS-Net: Stable Deep Networks from Non-Autonomous Differential Equations NeurIPS 2018 Rearranging the Familiar: Testing Compositional Generalization in Recurrent Networks EMNLP 2018 The Effect of Network Width on the Performance of Large-batch Training NeurIPS 2018 Do Deep Nets Really Need to be Deep? NeurIPS 2014 How transferable are features in deep neural networks? NeurIPS 2014 Smoothness, Low Noise and Fast Rates NeurIPS 2010