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 2206.02455math.STcs.ITcs.LGmath.ITstat.TH
收藏

高维二元Markov-Gaussian混合模型的均值估计

Mean Estimation in High-Dimensional Binary Markov Gaussian Mixture Models

Institute of Science and Technology, Austria(奥地利科学技术研究所);Technion - Israel Institute of Technology(以色列理工学院)

Yihan Zhang, Nir Weinberger

摘要:

我们考虑一个高维均值估计问题的二进制隐马尔可夫模型,它阐明了记忆数据,样本大小,尺寸和信号强度之间的相互作用,在统计推断。在该模型中,估计器观测$d$维参数向量$θ_{*}\in\mathbb{R}^{d}$的$n$样本,乘以随机符号$ S_i $($1\le i\le n$),并被各向同性标准高斯噪声破坏.符号序列$\{S_{i}\}_{i\in[n]}\in\{-1,1\}^{n}$是从具有翻转概率$δ\in[0,1/2]$的平稳齐次马尔可夫链中得出的。当$δ$变化时,该模型平滑地内插两个充分研究的模型:$δ=0$的高斯位置模型和$δ=1/2$的高斯混合模型。假设估计器知道$δ$,我们建立了一个近似极小极大最优(对数因子)估计误差率,作为$\|θ_{*}\|,δ,d,n$的函数。然后,我们提供了一个上限的情况下估计$δ$,假设(可能不准确)的知识$θ_{*}$。当$θ_{*}$是一个精确已知的常数时,证明了该界是紧的.这些结果,然后结合到一个算法,估计$θ_{*}$与$δ$未知的先验,其误差的理论保证。

英文摘要:

We consider a high-dimensional mean estimation problem over a binary hidden Markov model, which illuminates the interplay between memory in data, sample size, dimension, and signal strength in statistical inference. In this model, an estimator observes $n$ samples of a $d$-dimensional parameter vector $θ_{*}\in\mathbb{R}^{d}$, multiplied by a random sign $ S_i $ ($1\le i\le n$), and corrupted by isotropic standard Gaussian noise. The sequence of signs $\{S_{i}\}_{i\in[n]}\in\{-1,1\}^{n}$ is drawn from a stationary homogeneous Markov chain with flip probability $δ\in[0,1/2]$. As $δ$ varies, this model smoothly interpolates two well-studied models: the Gaussian Location Model for which $δ=0$ and the Gaussian Mixture Model for which $δ=1/2$. Assuming that the estimator knows $δ$, we establish a nearly minimax optimal (up to logarithmic factors) estimation error rate, as a function of $\|θ_{*}\|,δ,d,n$. We then provide an upper bound to the case of estimating $δ$, assuming a (possibly inaccurate) knowledge of $θ_{*}$. The bound is proved to be tight when $θ_{*}$ is an accurately known constant. These results are then combined to an algorithm which estimates $θ_{*}$ with $δ$ unknown a priori, and theoretical guarantees on its error are stated.

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。

↑