Accelerating cross-validation with total variation and its application to super-resolution imaging

We develop an approximation formula for the cross-validation error (CVE) of a sparse linear regression penalized by ℓ1-norm and total variation terms, which is based on a perturbative expansion utilizing the largeness of both the data dimensionality and the model. The developed formula allows us to reduce the necessary computational cost of the CVE evaluation significantly. The practicality of the formula is tested through application to simulated black-hole image reconstruction on the event-horizon scale with super resolution. The results demonstrate that our approximation reproduces the CVE values obtained via literally conducted cross-validation with reasonably good precision.

[1]  Alan E. E. Rogers,et al.  230 GHz VLBI OBSERVATIONS OF M87: EVENT‐HORIZON‐SCALE STRUCTURE DURING AN ENHANCED VERY‐HIGH‐ENERGY γ ?> ‐RAY STATE IN 2012 , 2015, 1505.03545.

[2]  L. Rudin,et al.  Nonlinear total variation based noise removal algorithms , 1992 .

[3]  William T. Freeman,et al.  Computational Imaging for VLBI Image Reconstruction , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[4]  K. Bouman,et al.  HIGH-RESOLUTION LINEAR POLARIMETRIC IMAGING FOR THE EVENT HORIZON TELESCOPE , 2016, 1605.06156.

[5]  Kazunori Akiyama,et al.  Super-resolution imaging with radio interferometry using sparse modeling , 2014, 1407.2422.

[6]  Kabashima Yoshiyuki,et al.  Approximate cross-validation formula for Bayesian linear regression , 2016 .

[7]  Yoshiyuki Kabashima,et al.  Cross validation in LASSO and its acceleration , 2015, ArXiv.

[8]  M. Nikolova.  An Algorithm for Total Variation Minimization and Applications , 2004 .

[9]  Genady Grabarnik,et al.  Sparse Modeling: Theory, Algorithms, and Applications , 2014 .

[10]  Trevor Hastie,et al.  Statistical Learning with Sparsity: The Lasso and Generalizations , 2015 .

[11]  Tony F. Chan,et al.  The digital TV filter and nonlinear denoising , 2001, IEEE Trans. Image Process..

[12]  Kazunori Akiyama,et al.  PRECL: A new method for interferometry imaging from closure phase , 2016, 1603.07078.

[13]  Marc Teboulle,et al.  Fast Gradient-Based Algorithms for Constrained Total Variation Image Denoising and Deblurring Problems , 2009, IEEE Transactions on Image Processing.

[14]  C. H. Ling,et al.  OGLE-2012-BLG-0950Lb: THE FIRST PLANET MASS MEASUREMENT FROM ONLY MICROLENS PARALLAX AND LENS FLUX , 2016, 1607.03267.

[15]  Kazunori Akiyama,et al.  Superresolution Full-polarimetric Imaging for Radio Interferometry with Sparse Modeling , 2017, 1702.00424.

[16]  R. Tibshirani.  Regression Shrinkage and Selection via the Lasso , 1996 .

[17]  M. Kino,et al.  White Paper on East Asian Vision for mm/submm VLBI: Toward Black Hole Astrophysics down to Angular Resolution of 1~R$_{S}$ , 2017 .

[18]  Jean Ponce,et al.  Sparse Modeling for Image and Vision Processing , 2014, Found. Trends Comput. Graph. Vis..

[19]  Feng Li,et al.  The application of compressive sampling to radio astronomy I: Deconvolution , 2011, 1106.1711.

[20]  P. Vandergheynst,et al.  Compressed sensing imaging techniques for radio interferometry , 2008, 0812.4933.

[21]  Kazunori Akiyama,et al.  Imaging black holes with sparse modeling , 2016 .

[22]  M. Gerin,et al.  HERSCHEL/HIFI SPECTRAL MAPPING OF C+, CH+, AND CH IN ORION BN/KL: THE PREVAILING ROLE OF ULTRAVIOLET IRRADIATION IN CH+ FORMATION , 2016, 1604.05805.

[23]  Yoshiyuki Kabashima,et al.  Approximate cross-validation formula for Bayesian linear regression , 2016, 2016 54th Annual Allerton Conference on Communication, Control, and Computing (Allerton).

[24]  K. Bouman,et al.  Imaging the Schwarzschild-radius-scale Structure of M87 with the Event Horizon Telescope Using Sparse Modeling , 2017, 1702.07361.