arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2307.00474cs.DScs.LG
收藏

矩、随机游走与谱近似极限

Moments, Random Walks, and Limits for Spectrum Approximation

Stanford University(斯坦福大学);New York University(纽约大学)

Yujia Jin, Christopher Musco, Aaron Sidford, Apoorv Vikram Singh

AI总结:

我们研究了一维分布矩近似问题的下界,证明存在无法通过已知所有矩来高精度近似的分布,并指出改进谱近似算法对 $1/\epsilon$ 的依赖性需新方法。

摘要:

我们研究在给定(含噪声的)矩测量条件下近似一维分布的下界。我们证明,存在定义在 $[-1,1]$ 上的分布,即使已知其所有矩达到乘性精度 $(1\pm2^{-1\Omega(1/\epsilon)})$,也无法在 Wasserstein-1 距离下近似到精度 $ε$;该结果与 Kong and Valiant [Annals of Statistics, 2017] 的上界匹配。为获得该结果,我们提供了一个困难实例,涉及由精心构造的图邻接矩阵特征值诱导的分布。在 Wasserstein-1 距离下高效近似此类谱是研究充分的算法问题,Cohen-Steiner 等人 [2017] 的一个上界,而最近的结果 [KDD 2018] 给出了一种一个基于精确近似谱矩的方法,使用从均匀随机节点开始的动的 $2^{O(1/\epsilon)}$ 随机游走。作为主要结果的强化,我们证明,改进该结果对 $1/\epsilon$ 的依赖性将需要新的算法途径。具体而言,没有算法能在常数概率下计算归一化图邻接矩阵谱的 $\epsilon$ 精确近似,即使给定从随机节点出发的长度为 $2^{\Omega(1/\epsilon)}$ 的 $2^{\Omega(1/\epsilon)}$ 随机游epsilon)}$ 随机游走的记录。

英文摘要:

We study lower bounds for the problem of approximating a one dimensional distribution given (noisy) measurements of its moments. We show that there are distributions on $[-1,1]$ that cannot be approximated to accuracy $ε$ in Wasserstein-1 distance even if we know \emph{all} of their moments to multiplicative accuracy $(1\pm2^{-Ω(1/ε)})$; this result matches an upper bound of Kong and Valiant [Annals of Statistics, 2017]. To obtain our result, we provide a hard instance involving distributions induced by the eigenvalue spectra of carefully constructed graph adjacency matrices. Efficiently approximating such spectra in Wasserstein-1 distance is a well-studied algorithmic problem, and a recent result of Cohen-Steiner et al. [KDD 2018] gives a method based on accurately approximating spectral moments using $2^{O(1/ε)}$ random walks initiated at uniformly random nodes in the graph. As a strengthening of our main result, we show that improving the dependence on $1/ε$ in this result would require a new algorithmic approach. Specifically, no algorithm can compute an $ε$-accurate approximation to the spectrum of a normalized graph adjacency matrix with constant probability, even when given the transcript of $2^{Ω(1/ε)}$ random walks of length $2^{Ω(1/ε)}$ started at random nodes.

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。

↑