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 2406.06106cs.LGcs.DS
收藏

可测试地学习多项式阈值函数

Testably Learning Polynomial Threshold Functions

ETH Zurich(苏黎世联邦理工学院)

Lucas Slot, Stefan Tiegel, Manuel Wiedmer

AI总结:

本文研究可测试学习多项式阈值函数,证明任意常数次PTF可在$n^{\mathrm{poly}(1/\varepsilon)}$时间内学习至超额误差$\varepsilon$,与不可知论模型匹配,并揭示其与矩匹配愚弄的联系。

摘要:

Rubinfeld和Vasilyan最近引入了可测试学习框架,作为经典不可知论模型的扩展。该框架通过测试器可高效检查的条件,放宽了难以验证的分布假设。当数据真正满足原始假设时,测试器必须接受,而当测试器接受时,学习器必须成功。我们关注测试器必须接受标准高斯数据的情形。已知在此情形下,诸如半空间等基本概念类可以以与(特定分布的)不可知论模型相同的时间复杂度进行可测试学习。在这项工作中,我们探讨为可测试地学习更复杂的概念类是否需要付出代价。特别地,我们考虑多项式阈值函数(PTFs),它自然地推广了半空间。我们证明,任意常数次的多项式阈值函数可以在时间$n^{\mathrm{poly}(1/\varepsilon)}$内可测试地学习,直至超额误差$\varepsilon > 0$。这在性质上与不可知论模型中已知的最佳保证相匹配。我们的结果建立在可测试学习与愚弄之间的联系之上。特别地,我们表明,近似匹配标准高斯至少$\mathrm{poly}(1/\varepsilon)$阶矩的分布可以愚弄常数次多项式阈值函数(直至误差$\varepsilon$)。作为次要结果,我们证明了一种直接证明可测试学习(无需愚弄)的方法,该方法曾成功用于半空间,但对于多项式阈值函数则不可行。

英文摘要:

Rubinfeld & Vasilyan recently introduced the framework of testable learning as an extension of the classical agnostic model. It relaxes distributional assumptions which are difficult to verify by conditions that can be checked efficiently by a tester. The tester has to accept whenever the data truly satisfies the original assumptions, and the learner has to succeed whenever the tester accepts. We focus on the setting where the tester has to accept standard Gaussian data. There, it is known that basic concept classes such as halfspaces can be learned testably with the same time complexity as in the (distribution-specific) agnostic model. In this work, we ask whether there is a price to pay for testably learning more complex concept classes. In particular, we consider polynomial threshold functions (PTFs), which naturally generalize halfspaces. We show that PTFs of arbitrary constant degree can be testably learned up to excess error $\varepsilon > 0$ in time $n^{\mathrm{poly}(1/\varepsilon)}$. This qualitatively matches the best known guarantees in the agnostic model. Our results build on a connection between testable learning and fooling. In particular, we show that distributions that approximately match at least $\mathrm{poly}(1/\varepsilon)$ moments of the standard Gaussian fool constant-degree PTFs (up to error $\varepsilon$). As a secondary result, we prove that a direct approach to show testable learning (without fooling), which was successfully used for halfspaces, cannot work for PTFs.

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。

↑