paper-with-me

Papers

On Bridging the Gap between Mean Field and Finite Width in Deep Random Neural Networks with Batch Normalization

2022-05-25 · Amir Joudaki, Hadi Daneshmand, Francis Bach

Mean field theory is widely used in the theoretical studies of neural networks. In this paper, we analyze the role of depth in the concentration of mean-field predictions, specifically for deep multilayer perceptron (MLP) with batch normalization (BN) at initialization. By scaling the network width to infinity, it is postulated that the mean-field predictions suffer from layer-wise errors that amplify with depth. We demonstrate that BN stabilizes the distribution of representations that avoids the error propagation of mean-field predictions. This stabilization, which is characterized by a geometric mixing property, allows us to establish concentration bounds for mean field predictions in infinitely-deep neural networks with a finite width.

📄 PDF Abstract BibTeX arXiv:2205.13076

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Batch Normalization 설명 없음

Similar Papers 제목 키워드 기반

Width-Robust Learnability in Mean-Field Bayesian Neural Networks

2026-07-07 · Dmitry Vaintrob, Kaarel Hänni arxiv

Infinite-width limits are a standard way to reason about neural networks, but it is not automatic that the limiting learner has the same complexity-theoretic inductive bias as large finite networks. We study this questio…

Global convergence of ResNets: From finite to infinite width using linear parameterization

2021-12-10 · Raphaël Barboni, Gabriel Peyré, François-Xavier Vialard

Overparametrization is a key factor in the absence of convexity to explain global convergence of gradient descent (GD) for neural networks. Beside the well studied lazy regime, infinite width (mean field) analysis has be…

Gauge-covariant stochastic neural fields: Stability and finite-width effects

2025-08-26 · Rodrigo Carmo Terin arxiv

We develop a gauge-covariant stochastic effective field theory for stability and finite-width effects in deep neural systems. The model uses classical commuting fields: a complex matter field, a real Abelian connection f…

Dynamically Stable Infinite-Width Limits of Neural Classifiers

2020-09-28 · Eugene Golikov

Recent research has been focused on two different approaches to studying neural networks training in the limit of infinite width (1) a mean-field (MF) and (2) a constant neural tangent kernel (NTK) approximations. These …

Binary Classification

Dynamically Stable Infinite-Width Limits of Neural Classifiers

2020-06-11 · Eugene. A. Golikov

Recent research has been focused on two different approaches to studying neural networks training in the limit of infinite width (1) a mean-field (MF) and (2) a constant neural tangent kernel (NTK) approximations. These …