FrOGS: Discrete Neural Sampler for Independent Alloy Configurations Across Chemical Conditions

2026-09-01

AI Summary

本文提出FrOGS，一种结合自回归模型和连续时间马尔可夫链的离散神经采样器，以解决合金在不同化学条件下热力学性质预测的问题。

Abstract

Predicting the thermodynamic properties of an alloy requires sampling its configurations across many chemical conditions and recovering free energies on a common absolute scale. Markov chain Monte Carlo (MCMC) is the standard tool, but it requires separate simulations at different conditions, and auxiliary free-energy methods such as thermodynamic integration are used to place results on a common absolute scale. Modern discrete neural samplers typically use reverse KL divergence as the objective and can be mode-seeking or biased. We present Free energy Offering Generative Sampler (FrOGS), a hybrid discrete neural sampler that couples an autoregressive model to a continuous-time Markov chain (CTMC) to be trained jointly under a single shared loss. FrOGS draws i.i.d. configurations, returns an unbiased estimate of the partition function, and gives consistent estimates of thermodynamic observables. We train a single model across a wide range of chemical conditions to produce estimates on a common absolute free-energy scale. FrOGS matches exact finite-size results on the 2D Ising model and reference phase diagrams for AgPd and CuAu, without mode collapse. We additionally compare to SEGAL, a published autoregressive baseline, and find that only FrOGS recovers the stability range of the CuAu$_3$ phase.

Problem

• alloy configurations
• thermodynamic properties
• chemical conditions
• Markov chain Monte Carlo (MCMC)
• free energy

Innovation

• discrete neural sampler
• autoregressive model
• continuous-time Markov chain (CTMC)
• unbiased estimate
• partition function