conftrace_

infinite width

20 papers

Explore in graph

Co-occurring keywords

neural network (6616) kernel methods (1097) gaussian process (1200) neural tangent kernel (205) residual network (211) network width (21) random weight (14) neural network initialization (33) stochastic differential equation (181) deep neural network (1803)

Papers

Wide Neural Networks as Gaussian Processes: Lessons from Deep Equilibrium Models NIPS 2023
What Can Be Learnt With Wide Convolutional Neural Networks? ICML 2023
Width and Depth Limits Commute in Residual Networks ICML 2023
Wide stochastic networks: Gaussian limit and PAC-Bayesian training ALT 2023
Simplicity Bias in 1-Hidden Layer Neural Networks NIPS 2023
Transition to Linearity of General Neural Networks with Directed Acyclic Graph Architecture NIPS 2022
On global convergence of ResNets: From finite to infinite width using linear parameterization NIPS 2022
Empirical Phase Diagram for Three-layer Neural Networks with Infinite Width NIPS 2022
The Neural Covariance SDE: Shaped Infinite Depth-and-Width Networks at Initialization NIPS 2022
Doubly infinite residual neural networks: a diffusion process approach JMLR 2021
Adversarial Robustness Guarantees for Random Deep Neural Networks ICML 2021
On the Neural Tangent Kernel of Deep Networks with Orthogonal Initialization IJCAI 2021
Wide Neural Networks with Bottlenecks are Deep Gaussian Processes JMLR 2020
Infinite attention: NNGP and NTK for deep attention networks ICML 2020
Stable behaviour of infinitely wide deep neural networks AISTATS 2020
Wide Feedforward or Recurrent Neural Networks of Any Architecture are Gaussian Processes NIPS 2019
Graph Neural Tangent Kernel: Fusing Graph Neural Networks with Graph Kernels NIPS 2019
On Exact Computation with an Infinitely Wide Neural Net NIPS 2019
Kernelized Synaptic Weight Matrices ICML 2018
To go deep or wide in learning? AISTATS 2014