arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.06247cs.LGcs.DSstat.ML
收藏

带有恶意噪声的半空间的样本最优PAC学习

Sample-Optimal PAC Learning of Halfspaces with Malicious Noise

Stevens Institute of Technology(斯蒂文斯理工学院)

Jie Shen

摘要:

我们研究了Valiant(1985)的恶意噪声存在下$\mathbb{R}^d$中齐次半空间的有效PAC学习。这是一个具有挑战性的噪声模型,直到最近才在未标记数据分布是各向同性对数凹的温和条件下建立了接近最优的噪声容限界。然而,如何同时获得最优的样本复杂度仍然没有解决。在这项工作中,我们对Awasthi等人的算法进行了新的分析。(2017)并表明它基本上实现了$\tilde{O}(d)$的接近最佳样本复杂度界限,改进了$\tilde{O}(d^2)$的最佳已知结果。我们的主要成分是一个新的矩阵矩阵的合并,以约束良好分布的经验协方差矩阵的谱,结合Awasthi等人的本地化方案的仔细探索。(2017)。我们进一步将算法和分析扩展到Bshouty等人(2002)的更一般和更强的讨厌的噪声模型,表明仍然有可能在多项式时间内实现接近最佳的噪声容限和样本复杂度。

英文摘要:

We study efficient PAC learning of homogeneous halfspaces in $\mathbb{R}^d$ in the presence of malicious noise of Valiant (1985). This is a challenging noise model and only until recently has near-optimal noise tolerance bound been established under the mild condition that the unlabeled data distribution is isotropic log-concave. However, it remains unsettled how to obtain the optimal sample complexity simultaneously. In this work, we present a new analysis for the algorithm of Awasthi et al. (2017) and show that it essentially achieves the near-optimal sample complexity bound of $\tilde{O}(d)$, improving the best known result of $\tilde{O}(d^2)$. Our main ingredient is a novel incorporation of a matrix Chernoff-type inequality to bound the spectrum of an empirical covariance matrix for well-behaved distributions, in conjunction with a careful exploration of the localization schemes of Awasthi et al. (2017). We further extend the algorithm and analysis to the more general and stronger nasty noise model of Bshouty et al. (2002), showing that it is still possible to achieve near-optimal noise tolerance and sample complexity in polynomial time.

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。

↑