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 2402.09693math.STstat.TH
收藏

shuffled线性回归的精确信息论阈值

Sharp Information-Theoretic Thresholds for Shuffled Linear Regression

Leon Lufkin, Yihong Wu, Jiaming Xu

AI总结:

本文研究了shuffled线性回归问题,证明了在次线性区域d=o(n)下,精确恢复未知置换的信噪比阈值为n^4,几乎精确恢复的阈值为n^2。

摘要:

本文研究shuffled线性回归问题,其中线性模型中预测变量与响应变量之间的对应关系被一个潜在置换所混淆。具体而言,我们考虑模型 $y = Π_* X β_* + w$,其中 $X$ 是一个 $n \times d$ 标准高斯设计矩阵,$w$ 是逐项方差为 $σ^2$ 的高斯噪声,$Π_*$ 是一个未知的 $n \times n$ 置换矩阵,$β_*$ 是回归系数,同样是未知的。先前的工作表明,在大 $n$ 极限下,以高概率精确恢复未知置换的最小信噪比($\mathsf{SNR}$),即 $\lVert β_* \rVert^2/σ^2$,介于 $n^2$ 和 $n^C$ 之间(其中 $C$ 为某个绝对常数),且即使在 $d=1$ 的情况下,精确阈值也是未知的。我们证明,在整个次线性区域 $d=o(n)$ 中,精确恢复的阈值精确为 $\mathsf{SNR} = n^4$。作为我们分析的副产品,我们还确定了几乎精确恢复的精确阈值为 $\mathsf{SNR} = n^2$,此时除了一个消失比例的置换外,其余部分均可被重构。

英文摘要:

This paper studies the problem of shuffled linear regression, where the correspondence between predictors and responses in a linear model is obfuscated by a latent permutation. Specifically, we consider the model $y = Π_* X β_* + w$, where $X$ is an $n \times d$ standard Gaussian design matrix, $w$ is Gaussian noise with entrywise variance $σ^2$, $Π_*$ is an unknown $n \times n$ permutation matrix, and $β_*$ is the regression coefficient, also unknown. Previous work has shown that, in the large $n$-limit, the minimal signal-to-noise ratio ($\mathsf{SNR}$), $\lVert β_* \rVert^2/σ^2$, for recovering the unknown permutation exactly with high probability is between $n^2$ and $n^C$ for some absolute constant $C$ and the sharp threshold is unknown even for $d=1$. We show that this threshold is precisely $\mathsf{SNR} = n^4$ for exact recovery throughout the sublinear regime $d=o(n)$. As a by-product of our analysis, we also determine the sharp threshold of almost exact recovery to be $\mathsf{SNR} = n^2$, where all but a vanishing fraction of the permutation is reconstructed.

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。

↑