arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1705.05403cond-mat.dis-nnstat.ML
收藏

逆伊辛问题学习曲线的统计物理方法

A statistical physics approach to learning curves for the Inverse Ising problem

Ludovica Bachschmid-Romano, Manfred Opper

摘要:

本文利用统计物理的方法,分析了大伊辛模型从独立数据学习耦合的误差(伊辛反问题)。我们专注于基于局部成本函数的学习,例如伪似然方法,其耦合对于每个自旋独立地推断。假设数据是从一个真正的伊辛模型产生的,我们计算的耦合的重建误差使用的副本方法与密集连接系统的腔方法相结合。我们表明,基于二次成本函数的显式估计实现了最小的重建误差,但需要作为先验知识的真实耦合向量的长度。一个简单的平均场估计的耦合,不需要这样的知识是渐近最优的,即当观察的数量是远远大于自旋的数量。理论与数值模拟的比较表明,从两个模型产生的数据与随机耦合在高温区域:一个模型与独立的耦合(谢林顿-柯克帕特里克模型),和一个模型的耦合矩阵具有Wishart分布的良好协议。

英文摘要:

Using methods of statistical physics, we analyse the error of learning couplings in large Ising models from independent data (the inverse Ising problem). We concentrate on learning based on local cost functions, such as the pseudo-likelihood method for which the couplings are inferred independently for each spin. Assuming that the data are generated from a true Ising model, we compute the reconstruction error of the couplings using a combination of the replica method with the cavity approach for densely connected systems. We show that an explicit estimator based on a quadratic cost function achieves minimal reconstruction error, but requires the length of the true coupling vector as prior knowledge. A simple mean field estimator of the couplings which does not need such knowledge is asymptotically optimal, i.e. when the number of observations is much large than the number of spins. Comparison of the theory with numerical simulations shows excellent agreement for data generated from two models with random couplings in the high temperature region: a model with independent couplings (Sherrington-Kirkpatrick model), and a model where the matrix of couplings has a Wishart distribution.

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。

↑