Theory

Universal Approximation with Deep Narrow Networks COLT 2020 VECA: A Method for Detecting Overfitting in Neural Networks (Student Abstract) AAAI 2020 What Deep CNNs Benefit From Global Covariance Pooling: An Optimization Perspective CVPR 2020 A Convergence Theory for Deep Learning via Over-Parameterization ICML 2019 Adversarial Examples Are a Natural Consequence of Test Error in Noise ICML 2019 A Mean Field Theory of Quantized Deep Networks: The Quantization-Depth Trade-Off NeurIPS 2019 Approximate Feature Collisions in Neural Nets NeurIPS 2019 Are deep ResNets provably better than linear predictors? NeurIPS 2019 A Solvable High-Dimensional Model of GAN NeurIPS 2019 A Sufficient Condition for Convergences of Adam and RMSProp CVPR 2019 Beyond the Single Neuron Convex Barrier for Neural Network Certification NeurIPS 2019 Capacity Control of ReLU Neural Networks by Basis-Path Norm AAAI 2019 CNN-Cert: An Efficient Framework for Certifying Robustness of Convolutional Neural Networks AAAI 2019 Conditional Independence Testing using Generative Adversarial Networks NeurIPS 2019 Convergence of Gradient Descent on Separable Data AISTATS 2019 Convolutional Neural Networks on Non-uniform Geometrical Signals Using Euclidean Spectral Transformation ICLR 2019 Deep Dominance - How to Properly Compare Deep Neural Models ACL 2019 Deep Equilibrium Models NeurIPS 2019 Deep Neural Networks Learn Non-Smooth Functions Effectively AISTATS 2019 Deep Neural Networks with Multi-Branch Architectures Are Intrinsically Less Non-Convex AISTATS 2019 Deep ReLU Networks Have Surprisingly Few Activation Patterns NeurIPS 2019 Deep Scale-spaces: Equivariance Over Scale NeurIPS 2019 Depth Separations in Neural Networks: What is Actually Being Separated? COLT 2019 Efficient and Accurate Estimation of Lipschitz Constants for Deep Neural Networks NeurIPS 2019 Efficient Approximation of Deep ReLU Networks for Functions on Low Dimensional Manifolds NeurIPS 2019