No article text was recorded for this version.
finite-width approximation error
Version 1 of 121 papers28 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Quantitative Gaussian approximation of randomly initialized deep neural networks
- Blog: Quantitative Propagation of Chaos for SGD in Wide Neural Networks
- Blog: Propagation of Chaos for Mean-Field Langevin Dynamics and its Application to Model Ensemble
- Blog: Beyond NTK with Vanilla Gradient Descent: A Mean-Field Analysis of Neural Networks with Polynomial Width, Samples, and Time
- Blog: Quantitative convergence of trained neural networks to Gaussian processes
- Blog: On the Convergence Analysis of Over-Parameterized Variational Autoencoders: A Neural Tangent Kernel Perspective
- Blog: Non-asymptotic Performance Guarantees for Neural Estimation of f-Divergences
- Blog: Pruning at Initialisation through the lens of Graphon Limit: Convergence, Expressivity, and Generalisation
- Blog: On the Equivalence between Neural Network and Support Vector Machine
- Blog: Wide Feedforward or Recurrent Neural Networks of Any Architecture are Gaussian Processes
- Blog: Rate of Convergence of Polynomial Networks to Gaussian Processes
- Blog: Dynamics of Finite Width Kernel and Prediction Fluctuations in Mean Field Neural Networks
- Blog: Mean-field theory of two-layers neural networks: dimension-free bounds and kernel limit
- Blog: Neural tangent kernels, transportation mappings, and universal approximation
- Blog: Mathematical Aspects of Neural Networks
- Blog: Non-asymptotic approximations of neural networks by Gaussian processes
- Blog: Mean-field analysis for heavy ball methods: Dropout-stability, connectivity, and global convergence
- Blog: Limiting fluctuation and trajectorial stability of multilayer neural networks with mean field training
- Blog: Uniform-in-time propagation of chaos for the mean-field gradient Langevin dynamics
- Blog: Approximation Bounds for Random Neural Networks and Reservoir Systems
- Blog: The construction and approximation of neural networks operators with Gaussian activation function
History & citation
Current · Permanent link
- This direction split from Finite Width Corrections for Infinite Neural Network Limits (67% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_finite_width_approximation_error_ed29e82e,
title = {finite-width approximation error},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/finite-width-approximation-error/rdr_ed29e82e2e034ed7b69eb5eddddaa8be},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_finite_width_approximation_error_ed29e82e_v1,
title = {finite-width approximation error},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/finite-width-approximation-error/rdr_ed29e82e2e034ed7b69eb5eddddaa8be/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}