arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2207.09660math.OCmath.PRmath.STstat.MLstat.TH
收藏

广义秩一矩阵感知的交替最小化:从随机初始化得到的精确预测

Alternating minimization for generalized rank one matrix sensing: Sharp predictions from a random initialization

Kabir Aladin Chandrasekher, Mengqi Lou, Ashwin Pananjady

AI总结:

本文研究广义秩一矩阵感知问题,提出基于样本分割的交替最小化算法,并通过确定性递归给出从随机初始化出发的精确收敛保证,揭示非线性与噪声对收敛行为的影响。

摘要:

我们考虑在独立同分布高斯、秩一测量经过非线性变换并受噪声污染的情况下,估计秩-$1$矩阵因子的问题。针对两种典型的非线性选择,我们研究了一种自然的交替更新规则在该非凸优化问题中从随机初始化出发的收敛性质。通过推导一个即使在高维问题中也精确的确定性递归,我们给出了该算法样本分割版本的精确收敛保证。值得注意的是,虽然无限样本的总体更新不提供信息并暗示一步即可精确恢复,但该算法——以及我们的确定性预测——从随机初始化出发以几何速度收敛。我们的精确非渐近分析还揭示了该问题的若干其他细粒度性质,包括非线性与噪声水平如何影响收敛行为。在技术层面,我们的结果是通过证明当每次迭代使用$n$个观测值时,经验误差递归可以被我们的确定性序列在$n^{-1/2}$阶波动范围内预测而实现的。我们的技术利用了源自高维$M$-估计文献的留一法工具,并为在其他具有随机数据的高维优化问题中从随机初始化出发精确分析高阶迭代算法提供了一条途径。

英文摘要:

We consider the problem of estimating the factors of a rank-$1$ matrix with i.i.d. Gaussian, rank-$1$ measurements that are nonlinearly transformed and corrupted by noise. Considering two prototypical choices for the nonlinearity, we study the convergence properties of a natural alternating update rule for this nonconvex optimization problem starting from a random initialization. We show sharp convergence guarantees for a sample-split version of the algorithm by deriving a deterministic recursion that is accurate even in high-dimensional problems. Notably, while the infinite-sample population update is uninformative and suggests exact recovery in a single step, the algorithm -- and our deterministic prediction -- converges geometrically fast from a random initialization. Our sharp, non-asymptotic analysis also exposes several other fine-grained properties of this problem, including how the nonlinearity and noise level affect convergence behavior. On a technical level, our results are enabled by showing that the empirical error recursion can be predicted by our deterministic sequence within fluctuations of the order $n^{-1/2}$ when each iteration is run with $n$ observations. Our technique leverages leave-one-out tools originating in the literature on high-dimensional $M$-estimation and provides an avenue for sharply analyzing higher-order iterative algorithms from a random initialization in other high-dimensional optimization problems with random data.

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。

↑