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 1712.06245stat.MLcs.LGmath.OC
收藏

误指定非凸统计优化相位恢复算法

Misspecified Nonconvex Statistical Optimization for Phase Retrieval

Princeton University(普林斯顿大学);Pennsylvania State University(宾夕法尼亚州立大学);Georgia Institute of Technology(佐治亚理工学院);Northwestern University(西北大学);Carnegie Mellon University(卡内基梅隆大学)

Zhuoran Yang, Lin F. Yang, Ethan X. Fang, Tuo Zhao, Zhaoran Wang, Matey Neykov

摘要:

现有的非凸统计优化理论和方法主要依赖于底层“真”统计模型的正确规范。为了解决这个问题,我们采取驯服模型误指定的第一步,通过研究高维稀疏相位检索问题与误指定的链接函数。特别是,我们提出了一个简单的变体的阈值Wirtinger流算法,给定一个适当的初始化,线性收敛到一个估计与最佳的统计精度为一个广泛的家庭未知的链接函数。我们还提供了大量的数值实验来支持我们的理论研究结果。

英文摘要:

Existing nonconvex statistical optimization theory and methods crucially rely on the correct specification of the underlying "true" statistical models. To address this issue, we take a first step towards taming model misspecification by studying the high-dimensional sparse phase retrieval problem with misspecified link functions. In particular, we propose a simple variant of the thresholded Wirtinger flow algorithm that, given a proper initialization, linearly converges to an estimator with optimal statistical accuracy for a broad family of unknown link functions. We further provide extensive numerical experiments to support our theoretical findings.

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。

↑