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 2111.05320cs.DScs.ITmath.ITmath.STstat.MLstat.TH
收藏

随机图的鲁棒估计

Robust Estimation for Random Graphs

Jayadev Acharya, Ayush Jain, Gautam Kamath, Ananda Theertha Suresh, Huanyu Zhang

摘要:

研究了Erdens-Rényi随机图在$n$节点上的参数$p$的鲁棒估计问题,其中$γ$部分节点可能是不利损坏的.在显示的不足之处的典型估计,我们设计了一个计算效率的谱算法估计$p$的准确度$\tilde O(\sqrt{p(1-p)}/n + γ\sqrt{p(1-p)} /\sqrt{n}+ γ/n)$为$γ< 1/60$。此外,我们给出了一个低效的算法,具有类似的精度为所有$γ<1/2$,信息理论的限制。最后,我们证明了一个近似匹配的统计下界,表明我们的算法的误差是最佳的对数因子。

英文摘要:

We study the problem of robustly estimating the parameter $p$ of an Erdős-Rényi random graph on $n$ nodes, where a $γ$ fraction of nodes may be adversarially corrupted. After showing the deficiencies of canonical estimators, we design a computationally-efficient spectral algorithm which estimates $p$ up to accuracy $\tilde O(\sqrt{p(1-p)}/n + γ\sqrt{p(1-p)} /\sqrt{n}+ γ/n)$ for $γ< 1/60$. Furthermore, we give an inefficient algorithm with similar accuracy for all $γ<1/2$, the information-theoretic limit. Finally, we prove a nearly-matching statistical lower bound, showing that the error of our algorithms is optimal up to logarithmic factors.

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。

↑