What Neural Network Field Theory Can and Cannot Realise on a Computer

• URL: http://arxiv.org/abs/2608.21523v2
• Date: Thu, 27 Aug 2026 20:37:50 GMT
• Title: What Neural Network Field Theory Can and Cannot Realise on a Computer
• Abstract summary: We separate four versions of neural network field theory, according to whether the defining object is the finite width ensemble or its infinite width limit.<n>Of the two limit versions, one can be simulated in full and the other only in part, as only its smeared correlators are computable with a controlled error.<n>One dimension escapes the obstruction, yet positivity is shown to still fail there at every finite width for the cosine network.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: One aim of neural network field theory is to put a quantum or effective field theory on a computer, with the network ensemble itself as the theory. We ask how far that aim can be pushed for a function class regular enough to be computed with. Our main result is a no-go theorem with assumptions that hold for standard network architectures. We use it to separate four versions of neural network field theory, according to whether the defining object is the finite width ensemble or its infinite width limit, and whether the target we want to compute is a quantum or an effective field theory. Neither finite width interpretation is straightforwardly consistent. For finite width ensembles with finite variance at each point, the QFT interpretation fails reflection positivity, while the EFT interpretation establishes no scale separation by which the positivity violation can be placed outside its domain of validity. Of the two limit versions, one can be simulated in full and the other only in part, as only its smeared correlators are computable with a controlled error. As such, at the level of a controlled numerical computation, the QFT and EFT versions cannot be distinguished. One dimension escapes the obstruction, yet reflection positivity is shown to still fail there at every finite width for the cosine network. Two escapes from the theorem remain, giving up either finite variance at a point or exact rotation invariance, and we discuss both of these possibilities.

Related papers

• Floating-Point Neural Networks Are Provably Robust Universal Approximators [11.144011131237935]
  neural networks enjoy a more general interval universal approximation (IUA) theorem.<n>An open question is whether the IUA theorem still holds in the floating-point setting.<n>Our IUA theorem in the floating-point setting exhibits material differences from the real-valued setting.
  arXiv  Detail & Related papers  (2025-06-19T06:43:04Z)
• On Infinite Tensor Networks, Complementary Recovery and Type II Factors [39.58317527488534]
  We study local operator algebras at the boundary of infinite tensor networks.<n>We decompose the limiting Hilbert space and the algebras of observables in a way that keeps track of the entanglement in the network.
  arXiv  Detail & Related papers  (2025-03-31T18:00:09Z)
• A Near Complete Nonasymptotic Generalization Theory For Multilayer Neural Networks: Beyond the Bias-Variance Tradeoff [57.25901375384457]
  We propose a nonasymptotic generalization theory for multilayer neural networks with arbitrary Lipschitz activations and general Lipschitz loss functions.<n>In particular, it doens't require the boundness of loss function, as commonly assumed in the literature.<n>We show the near minimax optimality of our theory for multilayer ReLU networks for regression problems.
  arXiv  Detail & Related papers  (2025-03-03T23:34:12Z)
• Local theories with parallel realities and the epistemic view of the quantum state [1.2891210250935148]
  We introduce a general framework that combines the randomness of single-world theories with the coexistence of diverse instances.<n>This framework has relevance in quantum communication complexity and leads to novel technical questions.
  arXiv  Detail & Related papers  (2025-02-19T15:19:08Z)
• Neural Network Field Theories: Non-Gaussianity, Actions, and Locality [0.0]
  Both the path integral measure in field theory and ensembles of neural networks describe distributions over functions. An expansion in $1/N$ corresponds to interactions in the field theory, but others, such as in a small breaking of the statistical independence of network parameters, can also lead to interacting theories.
  arXiv  Detail & Related papers  (2023-07-06T18:00:01Z)
• Connecting classical finite exchangeability to quantum theory [45.76759085727843]
  Exchangeability is a fundamental concept in probability theory and statistics.<n>It allows to model situations where the order of observations does not matter.<n>It is well known that both theorems do not hold for finitely exchangeable sequences.
  arXiv  Detail & Related papers  (2023-06-06T17:15:19Z)
• A connection between probability, physics and neural networks [0.0]
  We illustrate an approach that can be exploited for constructing neural networks which a priori obeys physical laws. We start with a simple single-layer neural network (NN) but refrain from choosing the activation functions yet. The activation functions constructed in this way guarantee the NN to a priori obey the physics, up to the approximation error of non-infinite network width.
  arXiv  Detail & Related papers  (2022-09-26T14:40:09Z)
• On the Neural Tangent Kernel Analysis of Randomly Pruned Neural Networks [91.3755431537592]
  We study how random pruning of the weights affects a neural network's neural kernel (NTK) In particular, this work establishes an equivalence of the NTKs between a fully-connected neural network and its randomly pruned version.
  arXiv  Detail & Related papers  (2022-03-27T15:22:19Z)
• Unified Field Theory for Deep and Recurrent Neural Networks [56.735884560668985]
  We present a unified and systematic derivation of the mean-field theory for both recurrent and deep networks. We find that convergence towards the mean-field theory is typically slower for recurrent networks than for deep networks. Our method exposes that Gaussian processes are but the lowest order of a systematic expansion in $1/n$.
  arXiv  Detail & Related papers  (2021-12-10T15:06:11Z)
• Nonperturbative renormalization for the neural network-QFT correspondence [0.0]
  We study the concepts of locality and power-counting in this context. We provide an analysis in terms of the nonperturbative renormalization group using the Wetterich-Morris equation. Our aim is to provide a useful formalism to investigate neural networks behavior beyond the large-width limit.
  arXiv  Detail & Related papers  (2021-08-03T10:36:04Z)
• Lifting the Convex Conjugate in Lagrangian Relaxations: A Tractable Approach for Continuous Markov Random Fields [53.31927549039624]
  We show that a piecewise discretization preserves better contrast from existing discretization problems. We apply this theory to the problem of matching two images.
  arXiv  Detail & Related papers  (2021-07-13T12:31:06Z)
• Causal Expectation-Maximisation [70.45873402967297]
  We show that causal inference is NP-hard even in models characterised by polytree-shaped graphs. We introduce the causal EM algorithm to reconstruct the uncertainty about the latent variables from data about categorical manifest variables. We argue that there appears to be an unnoticed limitation to the trending idea that counterfactual bounds can often be computed without knowledge of the structural equations.
  arXiv  Detail & Related papers  (2020-11-04T10:25:13Z)
• Coupling-based Invertible Neural Networks Are Universal Diffeomorphism Approximators [72.62940905965267]
  Invertible neural networks based on coupling flows (CF-INNs) have various machine learning applications such as image synthesis and representation learning. Are CF-INNs universal approximators for invertible functions? We prove a general theorem to show the equivalence of the universality for certain diffeomorphism classes.
  arXiv  Detail & Related papers  (2020-06-20T02:07:37Z)
• Towards a General Theory of Infinite-Width Limits of Neural Classifiers [6.09170287691728]
  We show a framework that gives rise to a discrete-time MF limit. We show that both MF and NTK limits have considerable limitations in approximating finite-sized neural nets.
  arXiv  Detail & Related papers  (2020-03-12T16:27:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.