relu network

Deep ReLU Networks Have Surprisingly Few Activation Patterns NeurIPS 2019 Efficient Approximation of Deep ReLU Networks for Functions on Low Dimensional Manifolds NeurIPS 2019 Efficiently testing local optimality and escaping saddles for ReLU networks ICLR 2019 Fast Convergence of Natural Gradient Descent for Over-Parameterized Neural Networks NeurIPS 2019 Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networks ICML 2019 Generalization Bounds of Stochastic Gradient Descent for Wide and Deep Neural Networks NeurIPS 2019 Gradient Dynamics of Shallow Univariate ReLU Networks NeurIPS 2019 How do infinite width bounded norm networks look in function space? COLT 2019 Learning Distributions Generated by One-Layer ReLU Networks NeurIPS 2019 Learning One-hidden-layer ReLU Networks via Gradient Descent AISTATS 2019 Provable Certificates for Adversarial Examples: Fitting a Ball in the Union of Polytopes NeurIPS 2019 The role of over-parametrization in generalization of neural networks ICLR 2019 Understanding Impacts of High-Order Loss Approximations and Features in Deep Learning Interpretation ICML 2019 How to Start Training: The Effect of Initialization and Architecture NeurIPS 2018 Optimal approximation of continuous functions by very deep ReLU networks COLT 2018 Semidefinite relaxations for certifying robustness to adversarial examples NeurIPS 2018 Size-Noise Tradeoffs in Generative Networks NeurIPS 2018 The Multilinear Structure of ReLU Networks ICML 2018 Towards Fast Computation of Certified Robustness for ReLU Networks ICML 2018 An Analytical Formula of Population Gradient for two-layered ReLU network and its Applications in Convergence and Critical Point Analysis ICML 2017 Eigenvalue Decay Implies Polynomial-Time Learnability for Neural Networks NeurIPS 2017 Neural Networks and Rational Functions ICML 2017 On the Flatness of Loss Surface for Two-layered ReLU Networks ACML 2017 The Expressive Power of Neural Networks: A View from the Width NeurIPS 2017 Expressiveness of Rectifier Networks ICML 2016