2000 character limit reached
Renormalization in the neural network-quantum field theory correspondence (2212.11811v1)
Published 22 Dec 2022 in hep-th, cond-mat.dis-nn, cs.LG, and stat.ML
Abstract: A statistical ensemble of neural networks can be described in terms of a quantum field theory (NN-QFT correspondence). The infinite-width limit is mapped to a free field theory, while finite N corrections are mapped to interactions. After reviewing the correspondence, we will describe how to implement renormalization in this context and discuss preliminary numerical results for translation-invariant kernels. A major outcome is that changing the standard deviation of the neural network weight distribution corresponds to a renormalization flow in the space of networks.