当前位置: X-MOL 学术J. ACM › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
An Unrestricted Learning Procedure
Journal of the ACM ( IF 2.5 ) Pub Date : 2019-11-25 , DOI: 10.1145/3361699
Shahar Mendelson 1
Affiliation  

We study learning problems involving arbitrary classes of functions F , underlying measures μ, and targets Y . Because proper learning procedures, i.e., procedures that are only allowed to select functions in F , tend to perform poorly unless the problem satisfies some additional structural property (e.g., that F is convex), we consider unrestricted learning procedures that are free to choose functions outside the given class. We present a new unrestricted procedure whose sample complexity is almost the best that one can hope for and holds for (almost) any problem, including heavy-tailed situations. Moreover, the sample complexity coincides with what one could expect if F were convex, even when F is not. And if F is convex, then the unrestricted procedure turns out to be proper.

中文翻译:

不受限制的学习程序

我们研究涉及任意类函数的学习问题F、基础度量 μ 和目标. 因为恰当的学习过程,即只允许选择函数的过程F, 往往表现不佳,除非问题满足一些额外的结构属性(例如,F是凸的),我们认为不受限制的学习程序可以自由选择给定类之外的函数。我们提出了一种新的不受限制的程序,其样本复杂性几乎是人们可以期望的最好的,并且适用于(几乎)任何问题,包括重尾情况。此外,样本复杂性与人们所期望的一致,如果F是凸的,即使当F不是。而如果F是凸的,那么不受限制的过程证明是正确的。
更新日期:2019-11-25
down
wechat
bug