The autoregressive neural network architecture of the Boltzmann distribution of pairwise interacting spins systems

arXiv:2302.08347v3 Announce Type: replace-cross
Abstract: Generative Autoregressive Neural Networks (ARNNs) have recently demonstrated exceptional results in image and language generation tasks, contributing to the growing popularity of generative models in both scientific and commercial applications. This work presents an exact mapping of the Boltzmann distribution of binary pairwise interacting systems into autoregressive form. The resulting ARNN architecture has weights and biases of its first layer corresponding to the Hamiltonian's couplings and external fields, featuring widely used structures such as the …

abstract applications architecture arxiv boltzmann commercial cond-mat.dis-nn cond-mat.stat-mech cs.lg distribution generative generative models image language language generation mapping network network architecture networks neural network neural networks results scientific stat.ml systems tasks type work