arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1903.05046math.STcs.ITmath.ITmath.PRstat.TH
收藏

稀疏线性回归中的全有或全无现象

The All-or-Nothing Phenomenon in Sparse Linear Regression

Galen Reeves, Jiaming Xu, Ilias Zadik

摘要:

研究了从$n$噪声线性观测值$Y=Xβ+W$中恢复隐藏的二进制$k$ -稀疏$p$维向量$β$的问题,其中$X_{ij}$是独立同分布的. $\mathcal{N}(0,1)$和$W_i$为i.i.d.。$\mathcal{N}(0,σ^2)$。一个密切相关的假设检验问题是区分从该结构化模型生成的$(X,Y)$对与相应的空模型,其中$(X,Y)$由纯粹独立的高斯项组成。在低稀疏度$k=o(p)$和高信噪比$k/σ^2=Ω\left(1\right)$制度,我们建立了一个“全有或全无”的信息理论相变在一个临界样本大小$n^*=2 k\log \left(p/k\right) /\log \left(1+k/σ^2\right)$,解决了猜想\cite{gamarnikzadik}。具体来说,我们表明,如果$\liminf_{p\to \infty} n/n^*>1$,那么最大似然估计几乎完美地恢复隐藏的向量具有高概率,而且可以检测到的真实假设与消失的错误概率。相反,如果是$\limsup_{p\to \infty} n/n^*<1$,则从信息理论上讲,甚至不可能恢复隐藏向量支持的任意小但固定的部分,或者严格地比随机猜测更好地测试假设。我们的不可能性结果的证明建立在两个关键技术,这可能是独立的利益。首先,我们使用条件二阶矩方法来上界结构化模型和零模型之间的Kullback-Leibler(KL)分歧。其次,受著名的面积定理的启发,我们建立了一个下界的最小均方估计误差的隐藏向量之间的KL分歧的两个模型。

英文摘要:

We study the problem of recovering a hidden binary $k$-sparse $p$-dimensional vector $β$ from $n$ noisy linear observations $Y=Xβ+W$ where $X_{ij}$ are i.i.d. $\mathcal{N}(0,1)$ and $W_i$ are i.i.d. $\mathcal{N}(0,σ^2)$. A closely related hypothesis testing problem is to distinguish the pair $(X,Y)$ generated from this structured model from a corresponding null model where $(X,Y)$ consist of purely independent Gaussian entries. In the low sparsity $k=o(p)$ and high signal to noise ratio $k/σ^2=Ω\left(1\right)$ regime, we establish an `All-or-Nothing' information-theoretic phase transition at a critical sample size $n^*=2 k\log \left(p/k\right) /\log \left(1+k/σ^2\right)$, resolving a conjecture of \cite{gamarnikzadik}. Specifically, we show that if $\liminf_{p\to \infty} n/n^*>1$, then the maximum likelihood estimator almost perfectly recovers the hidden vector with high probability and moreover the true hypothesis can be detected with a vanishing error probability. Conversely, if $\limsup_{p\to \infty} n/n^*<1$, then it becomes information-theoretically impossible even to recover an arbitrarily small but fixed fraction of the hidden vector support, or to test hypotheses strictly better than random guess. Our proof of the impossibility result builds upon two key techniques, which could be of independent interest. First, we use a conditional second moment method to upper bound the Kullback-Leibler (KL) divergence between the structured and the null model. Second, inspired by the celebrated area theorem, we establish a lower bound to the minimum mean squared estimation error of the hidden vector in terms of the KL divergence between the two models.

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。

↑