arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1612.05024cond-mat.stat-mechcs.LGphysics.data-anstat.ML
收藏

伊辛模型的最优结构与参数学习

Optimal structure and parameter learning of Ising models

Los Alamos National Laboratory(洛斯阿拉莫斯国家实验室);Skolkovo Institute of Science and Technology(斯科尔科沃科学技术研究院)

Andrey Y. Lokhov, Marc Vuffray, Sidhant Misra, Michael Chertkov

摘要:

从二进制样本重建伊辛模型的结构和参数是从统计物理学和计算生物学到图像处理和机器学习的各种学科中具有实际重要性的问题。研究界的重点转向开发通用的重建算法,这是计算效率和需要最少量的昂贵的数据。我们介绍了一种新的方法,交互筛选,准确地估计模型参数使用局部优化问题。该算法可证明实现完美的图结构恢复与信息理论上的最佳数量的样本,特别是在低温制度,这是已知的是最难学习。通过对具有不同类型相互作用的各种拓扑结构的合成伊辛模型以及由D波量子计算机产生的真实数据进行广泛的数值测试来评估相互作用筛选的功效。研究表明,交互作用筛选法是一种精确、易处理、通用的求解伊辛反问题的最优方法。

英文摘要:

Reconstruction of structure and parameters of an Ising model from binary samples is a problem of practical importance in a variety of disciplines, ranging from statistical physics and computational biology to image processing and machine learning. The focus of the research community shifted towards developing universal reconstruction algorithms which are both computationally efficient and require the minimal amount of expensive data. We introduce a new method, Interaction Screening, which accurately estimates the model parameters using local optimization problems. The algorithm provably achieves perfect graph structure recovery with an information-theoretically optimal number of samples, notably in the low-temperature regime which is known to be the hardest for learning. The efficacy of Interaction Screening is assessed through extensive numerical tests on synthetic Ising models of various topologies with different types of interactions, as well as on a real data produced by a D-Wave quantum computer. This study shows that the Interaction Screening method is an exact, tractable and optimal technique universally solving the inverse Ising problem.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑