relu activation

Neural Networks are Convex Regularizers: Exact Polynomial-time Convex Optimization Formulations for Two-layer Networks ICML 2020 Neural Path Features and Neural Path Kernel : Understanding the role of gates in deep learning NeurIPS 2020 On the Number of Linear Regions of Convolutional Neural Networks ICML 2020 On the Tightness of Semidefinite Relaxations for Certifying Robustness to Adversarial Examples NeurIPS 2020 Over-parameterized Adversarial Training: An Analysis Overcoming the Curse of Dimensionality NeurIPS 2020 Statistical-Query Lower Bounds via Functional Gradients NeurIPS 2020 Superpolynomial Lower Bounds for Learning One-Layer Neural Networks using Gradient Descent ICML 2020 Transformation of ReLU-based recurrent neural networks from discrete-time to continuous-time ICML 2020 A Convergence Theory for Deep Learning via Over-Parameterization ICML 2019 Approximate Feature Collisions in Neural Nets NeurIPS 2019 Capacity Control of ReLU Neural Networks by Basis-Path Norm AAAI 2019 Complexity of Linear Regions in Deep Networks ICML 2019 Computing Linear Restrictions of Neural Networks NeurIPS 2019 Deep Neural Networks Learn Non-Smooth Functions Effectively AISTATS 2019 Gradient Descent Provably Optimizes Over-parameterized Neural Networks ICLR 2019 How degenerate is the parametrization of neural networks with the ReLU activation function? NeurIPS 2019 How do infinite width bounded norm networks look in function space? COLT 2019 Inverting Deep Generative models, One layer at a time NeurIPS 2019 Learning One-hidden-layer ReLU Networks via Gradient Descent AISTATS 2019 Learning Two Layer Rectified Neural Networks in Polynomial Time COLT 2019 Nearly-tight VC-dimension and Pseudodimension Bounds for Piecewise Linear Neural Networks JMLR 2019 On Learning Over-parameterized Neural Networks: A Functional Approximation Perspective NeurIPS 2019 On the Convergence Rate of Training Recurrent Neural Networks NeurIPS 2019 Piecewise Strong Convexity of Neural Networks NeurIPS 2019 Random deep neural networks are biased towards simple functions NeurIPS 2019