infinite width

Understanding Reconstruction Attacks with the Neural Tangent Kernel and Dataset Distillation ICLR 2024 Analyzing Tree Architectures in Ensembles via Neural Tangent Kernel ICLR 2023 Simplicity Bias in 1-Hidden Layer Neural Networks NeurIPS 2023 The Onset of Variance-Limited Behavior for Networks in the Lazy and Rich Regimes ICLR 2023 What Can Be Learnt With Wide Convolutional Neural Networks? ICML 2023 Wide Neural Networks as Gaussian Processes: Lessons from Deep Equilibrium Models NeurIPS 2023 Wide stochastic networks: Gaussian limit and PAC-Bayesian training ALT 2023 Width and Depth Limits Commute in Residual Networks ICML 2023 Empirical Phase Diagram for Three-layer Neural Networks with Infinite Width NeurIPS 2022 On global convergence of ResNets: From finite to infinite width using linear parameterization NeurIPS 2022 The Neural Covariance SDE: Shaped Infinite Depth-and-Width Networks at Initialization NeurIPS 2022 Transition to Linearity of General Neural Networks with Directed Acyclic Graph Architecture NeurIPS 2022 Adversarial Robustness Guarantees for Random Deep Neural Networks ICML 2021 Doubly infinite residual neural networks: a diffusion process approach JMLR 2021 On the Neural Tangent Kernel of Deep Networks with Orthogonal Initialization IJCAI 2021 The Recurrent Neural Tangent Kernel ICLR 2021 A Function Space View of Bounded Norm Infinite Width ReLU Nets: The Multivariate Case ICLR 2020 Infinite attention: NNGP and NTK for deep attention networks ICML 2020 Stable behaviour of infinitely wide deep neural networks AISTATS 2020 Wide Neural Networks with Bottlenecks are Deep Gaussian Processes JMLR 2020 Deep Convolutional Networks as shallow Gaussian Processes ICLR 2019 Graph Neural Tangent Kernel: Fusing Graph Neural Networks with Graph Kernels NeurIPS 2019 On Exact Computation with an Infinitely Wide Neural Net NeurIPS 2019 Wide Feedforward or Recurrent Neural Networks of Any Architecture are Gaussian Processes NeurIPS 2019 Deep Neural Networks as Gaussian Processes ICLR 2018