neural network theory

Local Identifiability of Deep ReLU Neural Networks: the Theory NeurIPS 2022 The Neural Covariance SDE: Shaped Infinite Depth-and-Width Networks at Initialization NeurIPS 2022 Theoretically Provable Spiking Neural Networks NeurIPS 2022 Universal Approximation Under Constraints is Possible with Transformers ICLR 2022 Universality of Group Convolutional Neural Networks Based on Ridgelet Analysis on Groups NeurIPS 2022 Adversarial Examples in Multi-Layer Random ReLU Networks NeurIPS 2021 Separation Results between Fixed-Kernel and Feature-Learning Probability Metrics NeurIPS 2021 Thinking Like Transformers ICML 2021 Generalization Error Bounds of Gradient Descent for Learning Over-Parameterized Deep ReLU Networks AAAI 2020 Hierarchical nucleation in deep neural networks NeurIPS 2020 Initialization of ReLUs for Dynamical Isometry NeurIPS 2019 Entropy and mutual information in models of deep neural networks NeurIPS 2018 Geometry of Neural Network Loss Surfaces via Random Matrix Theory ICML 2017 Towards Understanding the Invertibility of Convolutional Neural Networks IJCAI 2017 On the Representational Efficiency of Restricted Boltzmann Machines NeurIPS 2013 Rademacher and Gaussian Complexities: Risk Bounds and Structural Results JMLR 2002