Fast global convergence of gradient methods for high-dimensional statistical recovery
Name
Agarwal-2012-Fast global convergence of gradient methods for high-dimensional statistical recovery.pdf
Size
578.38 KB
Format
Adobe PDF
Checksum (MD5)
b05d01356a3fddce4c89082f30f81bc5
Author(s)
Agarwal, Alekh
Negahban, Sahand N.
Wainwright, Martin J.
Date Issued
October 2012
Journal
Annals of Statistics
Publisher
Institute of Mathematical Statistics
Citation
Agarwal, Alekh, Sahand Negahban, and Martin J. Wainwright. "Fast global convergence of gradient methods for high-dimensional statistical recovery." Annals of Statistics 40.5 (2012): 2452-2482. ©Institute of Mathematical Statistics
Version
Final published version
Abstract
Many statistical M-estimators are based on convex optimization problems formed by the combination of a data-dependent loss function with a norm-based regularizer. We analyze the convergence rates of projected gradient and composite gradient methods for solving such problems, working within a high-dimensional framework that allows the ambient dimension d to grow with (and possibly exceed) the sample size n. Our theory identifies conditions under which projected gradient descent enjoys globally linear convergence up to the statistical precision of the model, meaning the typical distance between the true unknown parameter θ[superscript ∗] and an optimal solution [ˆ over θ]. By establishing these conditions with high probability for numerous statistical models, our analysis applies to a wide range of M-estimators, including sparse linear regression using Lasso; group Lasso for block sparsity; log-linear models with regularization; low-rank matrix recovery using nuclear norm regularization; and matrix decomposition using a combination of the nuclear and ℓ[subscript 1] norms. Overall, our analysis reveals interesting connections between statistical and computational efficiency in high-dimensional estimation.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Massachusetts Institute of Technology. Laboratory for Information and Decision Systems
Terms of Use
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1214/12-AOS1032SUPP
