This paper establishes a precise high-dimensional asymptotic theory for boosting on separable data, taking statistical and computational perspectives. We consider a high-dimensional setting where the number of features (weak learners) $p$ scales with the sample size $n$, in an overparametrized regime. Under a class of statistical models, we provide an exact analysis of the generalization error of boosting when the algorithm interpolates the training data and maximizes the empirical $\ell_1$-margin. Further, we explicitly pin down the relation between the boosting test error and the optimal Bayes error, as well as the proportion of active features at interpolation (with zero initialization). In turn, these precise characterizations answer certain questions raised in \cite{breiman1999prediction, schapire1998boosting} surrounding boosting, under assumed data generating processes. At the heart of our theory lies an in-depth study of the maximum-$\ell_1$-margin, which can be accurately described by a new system of non-linear equations; to analyze this margin, we rely on Gaussian comparison techniques and develop a novel uniform deviation argument. Our statistical and computational arguments can handle (1) any finite-rank spiked covariance model for the feature distribution and (2) variants of boosting corresponding to general $\ell_q$-geometry, $q \in [1, 2]$. As a final component, via the Lindeberg principle, we establish a universality result showcasing that the scaled $\ell_1$-margin (asymptotically) remains the same, whether the covariates used for boosting arise from a non-linear random feature model or an appropriately linearized model with matching moments.
翻译:本文用统计和计算角度,为提升可分解的数据建立精确的高度空格理论。 我们考虑一个高维的设置, 在一个过度平衡的制度中, 将功能数( 弱学习者) $p美元比值与样本大小为美元。 在一组统计模型下, 我们提供精确的分析, 当算法对培训数据进行内插时, 将推升的概括错误化, 并最大化实证 $_ $ 美元比值。 此外, 我们明确确定振标测试错误与最佳贝亚差错误之间的关系, 以及内推法( 初始化为零 初始化为零 ) 的主动特性比例。 反过来, 这些精确的定性解析解答了在\ breaman1999 pregation中提出的问题, 在假设数据生成过程下, 围绕推升的推力模型模型值, 我们理论的核心在于对最高值_ ell_ 1 美元比值的深度研究, 这可以由非线性调调调基调基调的基调的基调值值值值值值值值差值值值值值值值值, ; 分析这个比值的比值, 我们用来测量比值的比值的基值, 或直判算的基值的基值, 任何基值的比值的基值的基值的比值的基值, 我们的比值的比值, 任何基值的计算法的计算法的比值, 任何基值, 。