We prove a universality theorem for learning with random features. Our result shows that, in terms of training and generalization errors, a random feature model with a nonlinear activation function is asymptotically equivalent to a surrogate linear Gaussian model with a matching covariance matrix. This settles a so-called Gaussian equivalence conjecture based on which several recent papers develop their results. Our method for proving the universality theorem builds on the classical Lindeberg approach. Major ingredients of the proof include a leave-one-out analysis for the optimization problem associated with the training process and a central limit theorem, obtained via Stein's method, for weakly correlated random variables.
翻译:我们用随机特性来证明我们学习的普遍性理论。 我们的结果表明,在培训和一般化错误方面,一个具有非线性激活功能的随机特征模型与一个具有匹配的共变矩阵的替代线性高斯模式无异。 这解决了一种所谓的高斯等同假设,根据这种假设,最近的一些论文可以得出结果。 我们证明普遍性理论的方法以经典林德伯格方法为基础。 证据的主要内容包括对与培训过程有关的优化问题进行一出不出的分析,并通过施泰因方法获得的中心限制参数,用于薄弱关联随机变量。