TY - JOUR
T1 - Agnostic estimation for misspecified phase retrieval models
AU - Neykov, Matey
AU - Wang, Zhaoran
AU - Liu, Han
N1 - Publisher Copyright:
© 2020 Matey Neykov, Zhaoran Wang, and Han Liu.
Copyright:
Copyright 2020 Elsevier B.V., All rights reserved.
PY - 2020/6
Y1 - 2020/6
N2 - The goal of noisy high-dimensional phase retrieval is to estimate an s-sparse parameter β∗∈ Rd from n realizations of the model Y = (XTβ∗)2 + ∈. Based on this model, we propose a significant semi-parametric generalization called misspecified phase retrieval (MPR), in which Y = f(XTβ∗, ∈) with unknown f and Cov(Y, (XTβ∗)2) > 0. For example, MPR encompasses Y = h(|XTβ∗|) + ∈ with increasing h as a special case. Despite the generality of the MPR model, it eludes the reach of most existing semi-parametric estimators. In this paper, we propose an estimation procedure, which consists of solving a cascade of two convex programs and provably recovers the direction of β∗. Furthermore, we prove that our procedure is minimax optimal over the class of MPR models. Interestingly, our minimax analysis characterizes the statistical price of misspecifying the link function in phase retrieval models. Our theory is backed up by thorough numerical results.
AB - The goal of noisy high-dimensional phase retrieval is to estimate an s-sparse parameter β∗∈ Rd from n realizations of the model Y = (XTβ∗)2 + ∈. Based on this model, we propose a significant semi-parametric generalization called misspecified phase retrieval (MPR), in which Y = f(XTβ∗, ∈) with unknown f and Cov(Y, (XTβ∗)2) > 0. For example, MPR encompasses Y = h(|XTβ∗|) + ∈ with increasing h as a special case. Despite the generality of the MPR model, it eludes the reach of most existing semi-parametric estimators. In this paper, we propose an estimation procedure, which consists of solving a cascade of two convex programs and provably recovers the direction of β∗. Furthermore, we prove that our procedure is minimax optimal over the class of MPR models. Interestingly, our minimax analysis characterizes the statistical price of misspecifying the link function in phase retrieval models. Our theory is backed up by thorough numerical results.
UR - http://www.scopus.com/inward/record.url?scp=85094872369&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85094872369&partnerID=8YFLogxK
M3 - Article
AN - SCOPUS:85094872369
VL - 21
SP - 1
EP - 39
JO - Journal of Machine Learning Research
JF - Journal of Machine Learning Research
SN - 1532-4435
ER -