CoRMF: Criticality-Ordered Recurrent Mean Field Ising Solver

arXiv:2403.03391v1 Announce Type: cross
Abstract: We propose an RNN-based efficient Ising model solver, the Criticality-ordered Recurrent Mean Field (CoRMF), for forward Ising problems. In its core, a criticality-ordered spin sequence of an $N$-spin Ising model is introduced by sorting mission-critical edges with greedy algorithm, such that an autoregressive mean-field factorization can be utilized and optimized with Recurrent Neural Networks (RNNs). Our method has two notable characteristics: (i) by leveraging the approximated tree structure of the underlying Ising graph, the newly-obtained …

abstract algorithm arxiv cond-mat.stat-mech core cs.lg factorization mean mission rnn solver sorting spin stat.ml type