论文标题
关于复制的模拟退火的一些评论
Some Remarks on Replicated Simulated Annealing
论文作者
论文摘要
最近，作者介绍了训练离散权重的神经网络的想法，使用经典模拟退火与从统计物理文献中知道的复制品Ansatz之间的混合。除其他观点外，他们声称他们的方法能够找到强大的配置。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，我们阐明标准以确保其收敛性，并在成功从配置中取样时进行研究。我们还使用合成和真实数据库进行实验。
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 explicit criteria to guarantee its convergence, and study when it successfully samples from configurations. We also perform experiments using synthetic and real data bases.
