neural tangent kernel

Neural Tangent Kernel Beyond the Infinite-Width Limit: Effects of Depth and Initialization ICML 2022 Neural Tangent Kernel Empowered Federated Learning ICML 2022 Non-Gaussian Tensor Programs NeurIPS 2022 On feature learning in neural networks with global convergence guarantees ICLR 2022 On the Generalization Power of the Overfitted Three-Layer Neural Tangent Kernel Model NeurIPS 2022 On the Spectral Bias of Convolutional Neural Tangent and Gaussian Process Kernels NeurIPS 2022 Optimization and Adaptive Generalization of Three layer Neural Networks ICLR 2022 Out of Distribution Detection via Neural Network Anchoring ACML 2022 Overcoming The Spectral Bias of Neural Value Approximation ICLR 2022 Random Gegenbauer Features for Scalable Kernel Methods ICML 2022 Real-Valued Backpropagation is Unsuitable for Complex-Valued Neural Networks NeurIPS 2022 Rethinking Influence Functions of Neural Networks in the Over-Parameterized Regime AAAI 2022 Reverse Engineering the Neural Tangent Kernel ICML 2022 Robustness in deep learning: The good (width), the bad (depth), and the ugly (initialization) NeurIPS 2022 Sample-Then-Optimize Batch Neural Thompson Sampling NeurIPS 2022 Self-Consistent Dynamical Field Theory of Kernel Evolution in Wide Neural Networks NeurIPS 2022 Single Model Uncertainty Estimation via Stochastic Data Centering NeurIPS 2022 Spectral Bias Outside the Training Set for Deep Networks in the Kernel Regime NeurIPS 2022 TCT: Convexifying Federated Learning using Bootstrapped Neural Tangent Kernels NeurIPS 2022 The merged-staircase property: a necessary and nearly sufficient condition for SGD learning of sparse functions on two-layer neural networks COLT 2022 The Spectral Bias of Polynomial Neural Networks ICLR 2022 Transition to Linearity of General Neural Networks with Directed Acyclic Graph Architecture NeurIPS 2022 Transition to Linearity of Wide Neural Networks is an Emerging Property of Assembling Weak Models ICLR 2022 Understanding Square Loss in Training Overparametrized Neural Network Classifiers NeurIPS 2022 Universality of empirical risk minimization COLT 2022