Transformer networks sample up to 180x180 2D Ising systems and 64x64 Edwards-Anderson systems by generating spin groups with probability approximations, yielding ~20x higher effective sample size than prior neural samplers at criticality.
Parisi, Order parameter for spin-glasses, Physical Review Letters 50 (1983) 1946
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
The annealed TAP complexity is the Legendre transform of a Parisi variational functional constrained by zero overlap mass, with a matching lower bound from Kac-Rice computation.
Incorporating probability priors into variational autoregressive networks reduces training burden and enables larger system sizes for sampling in the Ising and Edwards-Anderson models.
citing papers explorer
-
Sampling two-dimensional spin systems with transformers
Transformer networks sample up to 180x180 2D Ising systems and 64x64 Edwards-Anderson systems by generating spin groups with probability approximations, yielding ~20x higher effective sample size than prior neural samplers at criticality.
-
The Legendre structure of the TAP complexity for the Ising spin glass
The annealed TAP complexity is the Legendre transform of a Parisi variational functional constrained by zero overlap mass, with a matching lower bound from Kac-Rice computation.
-
Variational Autoregressive Networks with probability priors
Incorporating probability priors into variational autoregressive networks reduces training burden and enables larger system sizes for sampling in the Ising and Edwards-Anderson models.