{"title":"平滑稳健相位检索","authors":"Zhong Zheng, Lingzhou Xue","doi":"arxiv-2409.01570","DOIUrl":null,"url":null,"abstract":"The phase retrieval problem in the presence of noise aims to recover the\nsignal vector of interest from a set of quadratic measurements with infrequent\nbut arbitrary corruptions, and it plays an important role in many scientific\napplications. However, the essential geometric structure of the nonconvex\nrobust phase retrieval based on the $\\ell_1$-loss is largely unknown to study\nspurious local solutions, even under the ideal noiseless setting, and its\nintrinsic nonsmooth nature also impacts the efficiency of optimization\nalgorithms. This paper introduces the smoothed robust phase retrieval (SRPR)\nbased on a family of convolution-type smoothed loss functions. Theoretically,\nwe prove that the SRPR enjoys a benign geometric structure with high\nprobability: (1) under the noiseless situation, the SRPR has no spurious local\nsolutions, and the target signals are global solutions, and (2) under the\ninfrequent but arbitrary corruptions, we characterize the stationary points of\nthe SRPR and prove its benign landscape, which is the first landscape analysis\nof phase retrieval with corruption in the literature. Moreover, we prove the\nlocal linear convergence rate of gradient descent for solving the SRPR under\nthe noiseless situation. Experiments on both simulated datasets and image\nrecovery are provided to demonstrate the numerical performance of the SRPR.","PeriodicalId":501379,"journal":{"name":"arXiv - STAT - Statistics Theory","volume":"82 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Smoothed Robust Phase Retrieval\",\"authors\":\"Zhong Zheng, Lingzhou Xue\",\"doi\":\"arxiv-2409.01570\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The phase retrieval problem in the presence of noise aims to recover the\\nsignal vector of interest from a set of quadratic measurements with infrequent\\nbut arbitrary corruptions, and it plays an important role in many scientific\\napplications. However, the essential geometric structure of the nonconvex\\nrobust phase retrieval based on the $\\\\ell_1$-loss is largely unknown to study\\nspurious local solutions, even under the ideal noiseless setting, and its\\nintrinsic nonsmooth nature also impacts the efficiency of optimization\\nalgorithms. This paper introduces the smoothed robust phase retrieval (SRPR)\\nbased on a family of convolution-type smoothed loss functions. Theoretically,\\nwe prove that the SRPR enjoys a benign geometric structure with high\\nprobability: (1) under the noiseless situation, the SRPR has no spurious local\\nsolutions, and the target signals are global solutions, and (2) under the\\ninfrequent but arbitrary corruptions, we characterize the stationary points of\\nthe SRPR and prove its benign landscape, which is the first landscape analysis\\nof phase retrieval with corruption in the literature. Moreover, we prove the\\nlocal linear convergence rate of gradient descent for solving the SRPR under\\nthe noiseless situation. Experiments on both simulated datasets and image\\nrecovery are provided to demonstrate the numerical performance of the SRPR.\",\"PeriodicalId\":501379,\"journal\":{\"name\":\"arXiv - STAT - Statistics Theory\",\"volume\":\"82 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-03\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - STAT - Statistics Theory\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.01570\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - STAT - Statistics Theory","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.01570","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
The phase retrieval problem in the presence of noise aims to recover the
signal vector of interest from a set of quadratic measurements with infrequent
but arbitrary corruptions, and it plays an important role in many scientific
applications. However, the essential geometric structure of the nonconvex
robust phase retrieval based on the $\ell_1$-loss is largely unknown to study
spurious local solutions, even under the ideal noiseless setting, and its
intrinsic nonsmooth nature also impacts the efficiency of optimization
algorithms. This paper introduces the smoothed robust phase retrieval (SRPR)
based on a family of convolution-type smoothed loss functions. Theoretically,
we prove that the SRPR enjoys a benign geometric structure with high
probability: (1) under the noiseless situation, the SRPR has no spurious local
solutions, and the target signals are global solutions, and (2) under the
infrequent but arbitrary corruptions, we characterize the stationary points of
the SRPR and prove its benign landscape, which is the first landscape analysis
of phase retrieval with corruption in the literature. Moreover, we prove the
local linear convergence rate of gradient descent for solving the SRPR under
the noiseless situation. Experiments on both simulated datasets and image
recovery are provided to demonstrate the numerical performance of the SRPR.