Recently authors have introduced the idea of training discrete weights neural networks using a mix between classical simulated annealing and a replica ansatz known from the statistical physics literature. Among other points, they claim their method is able to find robust configurations. In this paper, we analyze this so called “replicated simulated annealing” algorithm. In particular, we give criteria to guarantee its convergence, and study when it successfully samples from configurations. We also perform experiments using synthetic and real data bases.

中文翻译：

---

关于复制模拟退火的一些说明

最近，作者介绍了使用经典模拟退火和从统计物理学文献中获知的副本ansatz之间的混合来训练离散权重神经网络的想法。除其他外，他们声称他们的方法能够找到可靠的配置。在本文中，我们分析了这种所谓的“复制模拟退火”算法。特别是，我们给出了保证其收敛性的标准，并研究了何时从配置中成功采样。我们还使用综合和真实数据库进行实验。