arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.06283math.STcs.LGmath.PRstat.TH
收藏

具有平均光滑度的函数:结构、算法和学习

Functions with average smoothness: structure, algorithms, and learning

Yair Ashlagi, Lee-Ad Gottlieb, Aryeh Kontorovich

摘要:

我们提出了一个程序的平均光滑性分析,有效地学习度量空间上的实值函数。我们没有使用Lipschitz常数作为正则化器,而是在每个点定义一个局部斜率,并将函数复杂度作为这些值的平均值。由于平均值可以显著小于最大值,因此这种复杂性度量可以产生相当尖锐的泛化边界-假设这些边界允许用我们的局部斜率平均值替换Lipschitz常数的改进。我们的第一个主要贡献是获得这样的分布敏感的界限。这需要克服许多技术挑战,其中最艰巨的挑战可能是限制{ \em empirical}覆盖数,这可能比环境数表现得更差。我们的组合结果是伴随着有效的算法,用于平滑的标签的随机样本,以及保证从样本到整个空间的扩展将继续,以高概率,平均平滑。一路上,我们发现了一个令人惊讶的丰富的组合和分析结构,在我们定义的函数类。

英文摘要:

We initiate a program of average smoothness analysis for efficiently learning real-valued functions on metric spaces. Rather than using the Lipschitz constant as the regularizer, we define a local slope at each point and gauge the function complexity as the average of these values. Since the mean can be dramatically smaller than the maximum, this complexity measure can yield considerably sharper generalization bounds -- assuming that these admit a refinement where the Lipschitz constant is replaced by our average of local slopes. Our first major contribution is to obtain just such distribution-sensitive bounds. This required overcoming a number of technical challenges, perhaps the most formidable of which was bounding the {\em empirical} covering numbers, which can be much worse-behaved than the ambient ones. Our combinatorial results are accompanied by efficient algorithms for smoothing the labels of the random sample, as well as guarantees that the extension from the sample to the whole space will continue to be, with high probability, smooth on average. Along the way we discover a surprisingly rich combinatorial and analytic structure in the function class we define.

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。

↑