关于感知机GREM的非层次推广
On a nonhierarchical generalization of the Perceptron GREM
摘要:
我们引入了一个非线性的,非分层的推广德里达的GREM和建立通过Sanov型大偏差分析既玻尔兹曼-吉布斯原理以及Parisi公式的限制自由能。根据Parisi理论的预测,自由能由所有Parisi泛函/分层结构上的极小值给出,其中原始模型可以是粗粒度的。
英文摘要:
We introduce a nonlinear, nonhierarchical generalization of Derrida's GREM and establish through a Sanov-type large deviation analysis both a Boltzmann-Gibbs principle as well as a Parisi formula for the limiting free energy. In line with the predictions of the Parisi theory, the free energy is given by the minimal value over all Parisi functionals/hierarchical structures in which the original model can be coarse-grained.
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。