# A Correspondence Between Random Neural Networks and Statistical Field Theory

arXiv: https://arxiv.org/abs/1710.06570 · HTML: https://mlsanity.com/paper/1710.06570/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Oct 2017.

## Built on by (most cited first, 14 of 14)

- [Nonperturbative renormalization for the neural network-QFT correspondence](https://mlsanity.com/paper/2108.01403/) (2021)
- [Structures of Neural Network Effective Theories](https://mlsanity.com/paper/2305.02334/) (2023)
- [Bayesian RG Flow in Neural Network Field Theories](https://mlsanity.com/paper/2405.17538/) (2024)
- [The Autodidactic Universe](https://mlsanity.com/paper/2104.03902/) (2021)
- [Renormalization in the neural network-quantum field theory correspondence](https://mlsanity.com/paper/2212.11811/) (2022)
- [Fermions and Supersymmetry in Neural Network Field Theories](https://mlsanity.com/paper/2511.16741/) (2025)
- [Bayesian Inference with Deep Weakly Nonlinear Networks](https://mlsanity.com/paper/2405.16630/) (2024)
- [Topological Effects in Neural Network Field Theory](https://mlsanity.com/paper/2604.02313/) (2026)
- [Spontaneous symmetry breaking and Goldstone modes for deep information propagation](https://mlsanity.com/paper/2605.14685/) (2026)
- [Exact marginal prior distributions of finite Bayesian neural networks](https://mlsanity.com/paper/2104.11734/) (2021)
- [Spinning Conformal Correlators from Neural Networks](https://mlsanity.com/paper/2608.15001/) (2026)
- [Scaling and Resizing Symmetry in Feedforward Networks](https://mlsanity.com/paper/2306.15015/) (2023)
- [Dynamical Isometry based Rigorous Fair Neural Architecture Search](https://mlsanity.com/paper/2307.02263/) (2023)
- [Bulk-boundary decomposition of neural networks](https://mlsanity.com/paper/2511.02003/) (2025)

## Abstract (arXiv)

A number of recent papers have provided evidence that practical design questions about neural networks may be tackled theoretically by studying the behavior of random networks. However, until now the tools available for analyzing random neural networks have been relatively ad-hoc. In this work, we show that the distribution of pre-activations in random neural networks can be exactly mapped onto lattice models in statistical physics. We argue that several previous investigations of stochastic networks actually studied a particular factorial approximation to the full lattice model. For random linear networks and random rectified linear networks we show that the corresponding lattice models in the wide network limit may be systematically approximated by a Gaussian distribution with covariance between the layers of the network. In each case, the approximate distribution can be diagonalized by Fourier transformation. We show that this approximation accurately describes the results of numerical simulations of wide random neural networks. Finally, we demonstrate that in each case the large scale behavior of the random networks can be approximated by an effective field theory.