arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1704.02598cs.GTcs.LGmath.STstat.TH
收藏

一种样本复杂性测度及其在最优拍卖学习中的应用

A Sample Complexity Measure with Applications to Learning Optimal Auctions

Microsoft Research(微软研究院)

Vasilis Syrgkanis

摘要:

我们引入了一个新的样本复杂性度量,我们称之为分裂样本增长率。对于任何假设$H$和大小为$m$的任何样本$S$,拆分样本增长率$\hatτ_H(m)$计算有多少不同的假设可以在大小为$m/2$的$S$的任何子样本上经验风险最小化输出。我们证明了期望泛化误差的上界是由$O\left(\sqrt{\frac{\log(\hatτ_H(2m))}{m}}\right)$。我们的结果是通过加强Rademacher复杂性分析的预期泛化误差。我们表明,这种样本复杂性的措施,大大简化了分析的样本复杂性的最优拍卖设计,在许多拍卖类研究的文献。它们的样本复杂度可以通过注意到在这些拍卖类中,任何样本或子样本上的ERM将选择等于样本中的一个点的参数来得出。

英文摘要:

We introduce a new sample complexity measure, which we refer to as split-sample growth rate. For any hypothesis $H$ and for any sample $S$ of size $m$, the split-sample growth rate $\hatτ_H(m)$ counts how many different hypotheses can empirical risk minimization output on any sub-sample of $S$ of size $m/2$. We show that the expected generalization error is upper bounded by $O\left(\sqrt{\frac{\log(\hatτ_H(2m))}{m}}\right)$. Our result is enabled by a strengthening of the Rademacher complexity analysis of the expected generalization error. We show that this sample complexity measure, greatly simplifies the analysis of the sample complexity of optimal auction design, for many auction classes studied in the literature. Their sample complexity can be derived solely by noticing that in these auction classes, ERM on any sample or sub-sample will pick parameters that are equal to one of the points in the sample.

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。

↑