HEP-THLGDec 8, 2025

Conformal Defects in Neural Network Field Theories

arXiv:2512.07946v13 citationsh-index: 2
Originality Incremental advance
AI Analysis

This work addresses a theoretical problem in physics and machine learning for researchers interested in field theories and neural networks, but it appears incremental as it builds on existing NN-FT constructions.

The authors tackled the problem of constructing conformally invariant defects in Neural Network Field Theories (NN-FTs) by introducing a new formalism, and they demonstrated it in two toy models of NN scalar field theories, developing an NN interpretation of an expansion similar to the defect OPE in two-point correlation functions.

Neural Network Field Theories (NN-FTs) represent a novel construction of arbitrary field theories, including those of conformal fields, through the specification of the network architecture and prior distribution for the network parameters. In this work, we present a formalism for the construction of conformally invariant defects in these NN-FTs. We demonstrate this new formalism in two toy models of NN scalar field theories. We develop an NN interpretation of an expansion akin to the defect OPE in two-point correlation functions in these models.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes