We provide (high probability) bounds on the condition number of random feature matrices. In particular, we show that if the complexity ratio $\frac{N}{m}$ where $N$ is the number of neurons and $m$ is the number of data samples scales like $\log^{-1}(N)$ or $\log(m)$, then the random feature matrix is well-conditioned. This result holds without the need of regularization and relies on establishing various concentration bounds between dependent components of the random feature matrix. Additionally, we derive bounds on the restricted isometry constant of the random feature matrix. We prove that the risk associated with regression problems using a random feature matrix exhibits the double descent phenomenon and that this is an effect of the double descent behavior of the condition number. The risk bounds include the underparameterized setting using the least squares problem and the overparameterized setting where using either the minimum norm interpolation problem or a sparse regression problem. For the least squares or sparse regression cases, we show that the risk decreases as $m$ and $N$ increase, even in the presence of bounded or random noise. The risk bound matches the optimal scaling in the literature and the constants in our results are explicit and independent of the dimension of the data.
翻译:我们提供了随机特性矩阵条件数的(高概率)界限。 特别是, 我们显示, 如果复杂比率 $\ frac{ n ⁇ m} $, 美元为神经元数, 美元为美元, 美元为美元, 美元为美元, 美元为美元, 美元为美元, 那么数据样本量( 如 $\log}-1}( N) 美元 或 美元 美元 美元 ), 那么随机特性矩阵条件( 美元 ), 则随机特性矩阵条件数( 美元 ) 提供了( 高概率 ) 。 因此, 随机特性矩阵条件( 美元 ) 提供了( 高概率 ) 。 这个结果不需要规范, 并依赖于随机特性矩阵各依附组成部分之间设定不同的浓度界限。 此外, 我们从随机特性矩阵限制的异差常数常数 中获取的回归常数 。 我们证明, 与回归问题有关的风险以美元和 美元 美元 美元 美元 。 我们证明 与回归问题有关的风险会降低 。