Neural Network Field Theory at Finite Width

Christian Ferko; Aaron Mutchler

hep-thAug 21, 2026

Neural Network Field Theory at Finite Width

Authors: Christian Ferko, Aaron Mutchler

Organizations: Department of Physics, Northeastern University, Boston, MA 02115, USA · The NSF Institute for Artificial Intelligence and Fundamental Interactions

Abstract

Under mild assumptions, any quantum mechanical (QM) model or quantum field theory (QFT) admits a representation in terms of an ensemble of neural networks with countably many random parameters. We investigate the features of NN-QM and NN-FT models with finitely many parameters, such as a feedforward network of width $N < \infty$ . We find that, generically, such models must violate one of the properties of conventional Euclidean QFTs, such as reflection positivity or cluster decomposition. We present several complementary ways of understanding which features can and cannot be preserved at finite $N$ , both in QM and in QFT.

Explore similar work

What Neural Network Field Theory Can and Cannot Realise on a Computer
Aug 21, 2026Thomas R. HarveyHigh-Energy Physics
The NSF AI Institute for Artificial Intelligence and Fundamental Interactions. Center for Theoretical Physics, Massachusetts Institute of Technology, 77 Massachusetts Avenue, Cambridge, MA 02139, USA.
Deep neural networks as lattice gauge theories
Aug 19, 2026Ro Jefferson, Shradha Ramakrishnan
Institute for Theoretical Physics, and Department of Information and Computing Sciences, Utrecht University, Princetonplein 5, 3584 CC Utrecht, The Netherlands
Spinning Conformal Correlators from Neural Networks
Aug 15, 2026Manas Dogra, James Halverson, Joydeep NaskarHigh-Energy Physics
Department of Physics, Northeastern University, Boston, MA, 02115, USA · The NSF AI Institute for Artificial Intelligence and Fundamental Interactions, Cambridge, MA, U.S.A. · Beijing Institute of Mathematical Sciences and Applications, Huaibei Town, Huairou District, Beijing 101408, China

Aug 21, 2026J/K move · Enter open · S save

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

Thomas R. Harvey

The NSF AI Institute for Artificial Intelligence and Fundamental Interactions. Center for Theoretical Physics, Massachusetts Institute of Technology, 77 Massachusetts Avenue, Cambridge, MA 02139, USA.

High-Energy Physics

Open paper AskPDF arXiv

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.

Abstract

Explore similar work

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

Deep neural networks as lattice gauge theories

Spinning Conformal Correlators from Neural Networks