This paper provides a framework to show the concentration of solutions $Y^*$ to convex minimizing problem where the objective function $\phi(X)(Y)$ depends on some random vector $X$ satisfying concentration of measure hypotheses. More precisely, the convex problem translates into a contractive fixed point equation that ensure the transmission of the concentration from $X$ to $Y^*$. This result is of central interest to characterize many machine learning algorithms which are defined through implicit equations (e.g., logistic regression, lasso, boosting, etc.). Based on our framework, we provide precise estimations for the first moments of the solution $Y^*$, when $X= (x_1,\ldots, x_n)$ is a data matrix of independent columns and $\phi(X)(y)$ writes as a sum $\frac{1}{n}\sum_{i=1}^n h_i(x_i^TY)$. That allows to describe the behavior and performance (e.g., generalization error) of a wide variety of machine learning classifiers.
翻译:本文提供了一个框架,以显示解决方案的集中程度,从而在目标函数$\phi(X)(Y) 取决于某种随机矢量 $X(X)(Y)(美元) 满足测量假设集中度的情况下尽量减少问题。 更准确地说, 曲线问题转化为一个合同性固定点方程式, 以确保将浓度从X美元转移到Y$(Y)( 美元) 。 这一结果对于通过隐含方程式( 如物流回归、 lasso、 推力等) 定义的许多机器学习算法的特点具有核心意义。 根据我们的框架, 我们为解决方案的最初时刻提供了精确估计值$( $)( X= (x_ 1,\ldots, x_n) 美元是一个独立列的数据矩阵和 $\phi( X)(y) 美元以美元=1\n h_i( x_i_i) 美元写成。 从而可以描述各种机器学习分类师的行为和表现( 例如, 一般错误) 。