arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.06277cs.LGcs.DS
收藏

基于$\mathcal{L}_2$ -多项式回归和傅立叶算法的不可知PAC学习

On Agnostic PAC Learning using $\mathcal{L}_2$-polynomial Regression and Fourier-based Algorithms

Purdue University(普渡大学)

Mohsen Heidari, Wojciech Szpankowski

摘要:

我们开发了一个框架,使用希尔伯特空间作为代理分析PAC学习问题的结构特性。我们考虑一个联合希尔伯特空间,它包含了真实标签和联合分布$D$下的预测之间的关系。我们证明了具有0-1损失的不可知PAC学习等价于Hilbert空间域中的优化。在我们的模型中,我们使用基于最小二乘法的方法重新审视PAC学习问题,例如$\mathcal{L}_2$多项式回归和Linial的低度算法。我们研究关于几个假设类的学习,例如半空间和多项式近似类(即,由固定次数多项式近似的函数)。我们证明了(在一些分布的假设下),这样的方法得到的泛化误差高达$2opt$与$opt$是最佳的错误的类。因此,我们展示泛化误差当$opt\leq 0.2$。

英文摘要:

We develop a framework using Hilbert spaces as a proxy to analyze PAC learning problems with structural properties. We consider a joint Hilbert space incorporating the relation between the true label and the predictor under a joint distribution $D$. We demonstrate that agnostic PAC learning with 0-1 loss is equivalent to an optimization in the Hilbert space domain. With our model, we revisit the PAC learning problem using methods based on least-squares such as $\mathcal{L}_2$ polynomial regression and Linial's low-degree algorithm. We study learning with respect to several hypothesis classes such as half-spaces and polynomial-approximated classes (i.e., functions approximated by a fixed-degree polynomial). We prove that (under some distributional assumptions) such methods obtain generalization error up to $2opt$ with $opt$ being the optimal error of the class. Hence, we show the tightest bound on generalization error when $opt\leq 0.2$.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑