No article text was recorded for this version.
infinite-width limit behavior
Version 2 of 2163 papers235 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Neural Network Gaussian Processes by Increasing Depth
- Blog: Gaussian Process Behaviour in Wide Deep Neural Networks
- Blog: Neural Network Gaussian Processes by Increasing Depth
- Blog: Deep Neural Networks as Gaussian Processes
- Blog: Gaussian Process Behaviour in Wide Deep Neural Networks
- Blog: Exact posterior distributions of wide Bayesian neural networks
- Blog: Tensor Programs I: Wide Feedforward or Recurrent Neural Networks of Any Architecture are Gaussian Processes
- Blog: Computing with Infinite Networks
- Blog: Large-width functional asymptotics for deep Gaussian neural networks
- Blog: On the relationship between multitask neural networks and multitask Gaussian Processes
- Blog: Infinite Neural Operators: Gaussian processes on functions
- Blog: Wide Neural Networks with Bottlenecks are Deep Gaussian Processes
- Blog: Random Neural Networks in the Infinite Width Limit as Gaussian Processes
- Blog: Deep Neural Networks as Gaussian Processes
- Blog: Quantitative CLTs in Deep Neural Networks
- Blog: Tensor Network-Constrained Kernel Machines as Gaussian Processes
- Blog: Simplifying Graph Kernels for Efficient
- Blog: Beyond IID weights: sparse and low-rank deep Neural Networks are also Gaussian Processes
- Blog: Wide Bayesian neural networks have a simple weight posterior: theory and accelerated sampling
- Blog: Infinite Neural Operators: Gaussian processes on functions
- Blog: Wide Feedforward or Recurrent Neural Networks of Any Architecture are Gaussian Processes
- Blog: Width and Depth Limits Commute in Residual Networks
- Blog: Bayesian Inference with Anchored Ensembles of Neural Networks, and Application to Reinforcement Learning
- Blog: Tensor Network-Constrained Kernel Machines as Gaussian Processes
- Blog: How (Implicit) Regularization of ReLU Neural Networks Characterizes the Learned Function - Part II: the Multi-D Case of Two Layers with Random First Layer
- Blog: Infinitely Wide Graph Convolutional Networks: Semi-supervised Learning via Gaussian Processes
- Blog: Neural Network Gaussian Processes by Increasing Depth
- Blog: Wide Deep Neural Networks with Gaussian Weights are Very Close to Gaussian Processes
- Blog: When and why PINNs fail to train: A neural tangent kernel perspective
- Blog: Uncertainty in Neural Networks: Approximately Bayesian Ensembling
- Blog: Deep Convolutional Networks as shallow Gaussian Processes
- Blog: Observation Noise and Initialization in Wide Neural Networks
- Blog: A Bayesian Perspective on the Deep Image Prior
- Blog: Towards Understanding Inductive Bias in Transformers: A View From Infinity
- Blog: Exploring the Uncertainty Properties of Neural Networks' Implicit Priors in the Infinite-Width Limit
- Blog: Estimating Causal Effects using a Multi-task Deep Ensemble
- Blog: The Ridgelet Prior: A Covariance Function Approach to Prior Specification for Bayesian Neural Networks
- Blog: Neural signature kernels as infinite-width-depth-limits of controlled ResNets
- Blog: Neural Tangents: Fast and Easy Infinite Neural Networks in Python
- Blog: Wide Bayesian neural networks have a simple weight posterior: theory and accelerated sampling
- Blog: Wide Neural Networks with Bottlenecks are Deep Gaussian Processes
- Blog: An Infinite-Width Analysis on the Jacobian-Regularised Training of a Neural Network
- Blog: A Bayesian Perspective on the Deep Image Prior
- Blog: Width and Depth Limits Commute in Residual Networks
- Blog: Deep Convolutional Networks as shallow Gaussian Processes
- Blog: Function-Space MCMC for Bayesian Wide Neural Networks
- Blog: Wide stochastic networks: Gaussian limit and PAC-Bayesian training
- Blog: Are wider nets better given the same number of parameters?
- Blog: Deep Maxout Network Gaussian Process
- Blog: A Primer on Bayesian Neural Networks: Review and Debates
- Blog: Deep learning generalizes because the parameter-function map is biased towards simple functions
- Blog: A theory of representation learning gives a deep generalisation of kernel methods
- Blog: Les Houches Lectures on Deep Learning at Large & Infinite Width
- Blog: Exploration Behavior of Untrained Policies
- Blog: Law of Large Numbers for Bayesian two-layer Neural Network trained with Variational Inference
- Blog: Finite Versus Infinite Neural Networks: an Empirical Study
- Blog: Finite Neural Networks as Mixtures of Gaussian Processes: From Provable Error Bounds to Prior Selection
- Blog: Finite Versus Infinite Neural Networks: an Empirical Study
- Blog: Gaussian Processes for Regression
- Blog: Adaptive Transfer Learning for Plant Phenotyping
Showing 60 of 163 papers.
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_infinite_width_limit_behavior_c638f5d2,
title = {infinite-width limit behavior},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/infinite-width-limit-behavior/rdr_c638f5d297f54114821977bc20ba9649},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 2, frozen text):
@misc{lacuna_infinite_width_limit_behavior_c638f5d2_v2,
title = {infinite-width limit behavior},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/infinite-width-limit-behavior/rdr_c638f5d297f54114821977bc20ba9649/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-20},
}