We provide exact asymptotic expressions for the performance of regression by an $L-$layer deep random feature (RF) model, where the input is mapped through multiple random embedding and non-linear activation functions. For this purpose, we establish two key steps: First, we prove a novel universality result for RF models and deterministic data, by which we demonstrate that a deep random feature model is equivalent to a deep linear Gaussian model that matches it in the first and second moments, at each layer. Second, we make use of the convex Gaussian Min-Max theorem multiple times to obtain the exact behavior of deep RF models. We further characterize the variation of the eigendistribution in different layers of the equivalent Gaussian model, demonstrating that depth has a tangible effect on model performance despite the fact that only the last layer of the model is being trained.
翻译:我们用一个 $L-$lay 深层随机特性( RF) 模型来进行回归, 输入通过多个随机嵌入和非线性激活功能绘制。 为此, 我们设定了两个关键步骤 : 首先, 我们证明RF 模型和确定性数据具有新的普遍性结果, 我们通过它来证明深层随机特性模型相当于一个深层直线高斯模型, 在每一层的第一和第二时刻与该模型相匹配。 其次, 我们多次使用 convex Gaussian Min- Max 光谱质模型, 以获得深层RF模型的确切行为。 我们进一步描述等高斯模型不同层的易发性变化, 表明深度对模型性能有实际影响, 尽管只对模型的最后一层进行了训练。