Teacher-student models provide a framework in which the typical-case performance of high-dimensional supervised learning can be described in closed form. The assumptions of Gaussian i.i.d. input data underlying the canonical teacher-student model may, however, be perceived as too restrictive to capture the behaviour of realistic data sets. In this paper, we introduce a Gaussian covariate generalisation of the model where the teacher and student can act on different spaces, generated with fixed, but generic feature maps. While still solvable in a closed form, this generalization is able to capture the learning curves for a broad range of realistic data sets, thus redeeming the potential of the teacher-student framework. Our contribution is then two-fold: First, we prove a rigorous formula for the asymptotic training loss and generalisation error. Second, we present a number of situations where the learning curve of the model captures the one of a realistic data set learned with kernel regression and classification, with out-of-the-box feature maps such as random projections or scattering transforms, or with pre-learned ones - such as the features learned by training multi-layer neural networks. We discuss both the power and the limitations of the framework.
翻译:教师-学生模式提供了一个框架,可以在其中以封闭的形式描述高层次监督教学的典型表现。高森i.d.的假设是,作为教师-学生模式基础的输入数据可能被认为过于严格,无法捕捉现实数据集的行为。在本文中,我们引入了高森共变式模型,使教师和学生能够在固定但通用地貌地图生成的不同空间上采取行动。虽然这种一般化仍然以封闭的形式可以溶解,但能够捕捉一系列广泛现实数据集的学习曲线,从而抵消教师-学生框架的潜力。我们的贡献有两重:首先,我们证明对无症状培训损失和概括错误的严格公式。第二,我们介绍了一些情况,模型的学习曲线能够捕捉到通过内核回归和分类学习的一套现实数据,并有外框地图,例如随机预测或分散式变换,或者通过我们学习的网络和多层次框架,例如通过学习的学习的网络和变压。