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 1907.04274cs.DS
收藏

傅里叶稀疏函数在离群点下的重构

Reconstruction under outliers for Fourier-sparse functions

Xue Chen, Anindya De

摘要:

我们考虑的问题学习一个未知的$f$稀疏傅立叶频谱中存在的离群噪声。特别地,该算法可以访问(未知的)$f$的噪声预言,使得(i)$f$的傅立叶谱是$k$ -稀疏的;(ii)在任何查询点$x$,预言返回$y$,使得概率为$1-ρ$,$|y-f(x)| \le ε$。然而,对于概率$ρ$,误差$y-f(x)$可以任意大。我们研究傅立叶稀疏函数的离散立方体$\{0,1\}^n$和环面$[0,1)$和这两个域,我们设计了有效的算法,可以容忍任何$ρ<1/2$分数的离群值。我们注意到,低次多项式的类似问题最近已经在几个作品中进行了研究[AK 03,GZ 16,KKP 17],并且在该设置中已知类似的算法保证。虽然我们的主要结果涉及的情况下,异常值的位置,即,$x$使得$|y-f(x)|>ε$是随机分布的,我们还研究了异常值位于相反位置的情况。特别是,我们表明,在环面上,假设傅立叶变换满足一定的\emph{granularity}条件,有一个样本有效的算法容忍$ρ=Ω(1)$分数的离群值和进一步,这是不可能的,没有这样的粒度条件。最后,虽然不是主要的推力,但我们的技术还允许我们在存在对抗性离群噪声的情况下在超立方体上学习低次函数$f$。我们的技术结合了压缩感知,稀疏傅立叶变换,链接参数和复杂分析的各种工具。

英文摘要:

We consider the problem of learning an unknown $f$ with a sparse Fourier spectrum in the presence of outlier noise. In particular, the algorithm has access to a noisy oracle for (an unknown) $f$ such that (i) the Fourier spectrum of $f$ is $k$-sparse; (ii) at any query point $x$, the oracle returns $y$ such that with probability $1-ρ$, $|y-f(x)| \le ε$. However, with probability $ρ$, the error $y-f(x)$ can be arbitrarily large. We study Fourier sparse functions over both the discrete cube $\{0,1\}^n$ and the torus $[0,1)$ and for both these domains, we design efficient algorithms which can tolerate any $ρ<1/2$ fraction of outliers. We note that the analogous problem for low-degree polynomials has recently been studied in several works~[AK03, GZ16, KKP17] and similar algorithmic guarantees are known in that setting. While our main results pertain to the case where the location of the outliers, i.e., $x$ such that $|y-f(x)|>ε$ is randomly distributed, we also study the case where the outliers are adversarially located. In particular, we show that over the torus, assuming that the Fourier transform satisfies a certain \emph{granularity} condition, there is a sample efficient algorithm to tolerate $ρ=Ω(1)$ fraction of outliers and further, that this is not possible without such a granularity condition. Finally, while not the principal thrust, our techniques also allow us non-trivially improve on learning low-degree functions $f$ on the hypercube in the presence of adversarial outlier noise. Our techniques combine a diverse array of tools from compressive sensing, sparse Fourier transform, chaining arguments and complex analysis.

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。

↑