Single-index models are a class of functions given by an unknown univariate ``link'' function applied to an unknown one-dimensional projection of the input. These models are particularly relevant in high dimension, when the data might present low-dimensional structure that learning algorithms should adapt to. While several statistical aspects of this model, such as the sample complexity of recovering the relevant (one-dimensional) subspace, are well-understood, they rely on tailored algorithms that exploit the specific structure of the target function. In this work, we introduce a natural class of shallow neural networks and study its ability to learn single-index models via gradient flow. More precisely, we consider shallow networks in which biases of the neurons are frozen at random initialization. We show that the corresponding optimization landscape is benign, which in turn leads to generalization guarantees that match the near-optimal sample complexity of dedicated semi-parametric methods.
翻译:单指数模型是一种由未知的单维函数“ link” 函数给定的功能类别, 适用于输入的未知的单维投影。 这些模型在高维方面特别相关, 因为数据可能会显示学习算法应该适应的低维结构。 虽然该模型的一些统计方面, 如恢复相关( 一维) 子空间的样本复杂性, 已经非常清楚, 它们依赖于利用目标函数特定结构的量身定制算法。 在这项工作中, 我们引入了浅浅神经网络的自然类别, 并研究其通过梯度流学习单一指数模型的能力。 更准确地说, 我们考虑的是神经元的偏向在随机初始化时被冻结的浅网络。 我们表明, 相应的优化景观是良性的, 这反过来又导致普遍化保证与专用半参数方法的近最佳样本复杂性相匹配。