{"ID":2886526,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.03810","arxiv_id":"2508.03810","title":"Viability of perturbative expansion for quantum field theories on neurons","abstract":"Neural Network (NN) architectures that break statistical independence of parameters have been proposed as a new approach for simulating local quantum field theories (QFTs). In the infinite neuron number limit, single-layer NNs can exactly reproduce QFT results. This paper examines the viability of this architecture for perturbative calculations of local QFTs for finite neuron number $N$ using scalar $φ^4$ theory in $d$ Euclidean dimensions as an example. We find that the renormalized $O(1/N)$ corrections to two- and four-point correlators yield perturbative series which are sensitive to the ultraviolet cut-off and therefore have a weak convergence. We propose a modification to the architecture to improve this convergence and discuss constraints on the parameters of the theory and the scaling of N which allow us to extract accurate field theory results.","short_abstract":"Neural Network (NN) architectures that break statistical independence of parameters have been proposed as a new approach for simulating local quantum field theories (QFTs). In the infinite neuron number limit, single-layer NNs can exactly reproduce QFT results. This paper examines the viability of this architecture for...","url_abs":"https://arxiv.org/abs/2508.03810","url_pdf":"https://arxiv.org/pdf/2508.03810v4","authors":"[\"Srimoyee Sen\",\"Varun Vaidya\"]","published":"2025-08-05T18:00:31Z","proceeding":"hep-th","tasks":"[\"hep-th\",\"cs.LG\"]","methods":"[]","has_code":false}