近似就足够好了：维数和边际复杂性的概率变量
Approximate is Good Enough: Probabilistic Variants of Dimensional and Margin Complexity
Toyota Technological Institute at Chicago（芝加哥丰田理工学院）
摘要：
我们提出和研究近似的概念，尺寸和利润的复杂性，这对应于最小的尺寸或规范的嵌入所需的近似，而不是准确地表示，一个给定的假设类。我们表明，这样的概念不仅是足够的学习使用线性预测或内核，但不像确切的变种，也是必要的。因此，它们更适合于讨论线性或核方法的局限性。
英文摘要：
We present and study approximate notions of dimensional and margin complexity, which correspond to the minimal dimension or norm of an embedding required to approximate, rather then exactly represent, a given hypothesis class. We show that such notions are not only sufficient for learning using linear predictors or a kernel, but unlike the exact variants, are also necessary. Thus they are better suited for discussing limitations of linear or kernel methods.
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。
