Fast Methods for Denoising Matrix Completion Formulations, with Applications to Robust Seismic Data Interpolation
Abstract
Recent SVD-free matrix factorization formulations have enabled rank minimization for systems with millions of rows and columns, paving the way for matrix completion in extremely large-scale applications, such as seismic data interpolation. In this paper, we consider matrix completion formulations designed to hit a target data-fitting error level provided by the user, and we propose an algorithm called LR-BPDN that is able to exploit factorized formulations to solve the corresponding optimization problem. Since practitioners typically have strong prior knowledge about target error level, this innovation makes it easy to apply the algorithm in practice, leaving only the factor rank to be determined. Within the established framework, we propose two extensions that are highly relevant to solving practical challenges of data interpolation. First, we propose a weighted extension that allows known subspace information to improve the results of matrix completion formulations. We show how this weighting can be used in the context of frequency continuation, an essential aspect to seismic data interpolation. Second, we propose matrix completion formulations that are robust to large measurement errors in the available data. We illustrate the advantages of LR-BPDN on collaborative filtering problems using the MovieLens 1M and 10M and Netflix 100M datasets. Then we use the new method, along with its robust and subspace reweighted extensions, to obtain high-quality reconstructions for large-scale seismic interpolation problems with real data, even in the presence of data contamination.
Keywords
MSC codes
Get full access to this article
View all available purchase options and get full access to this article.
References
1.
A. Y. Aravkin, J. V. Burke, and M. P. Friedlander, Variational properties of value functions, SIAM J. Optim., 23 (2013), pp. 1689--1717.
2.
A. Y. Aravkin, M. P. Friedlander, F. Herrmann, and T. van Leeuwen, Robust inversion, dimensionality reduction, and randomized sampling, Math. Program., 134 (2012), pp. 101--125.
3.
S. R. Becker, E. J. Candes, and M. C. Grant, Templates for convex cone problems with applications to sparse signal recovery, Math. Program. Comput., 3 (2011), pp. 165--218.
4.
S. Burer and R. D. C. Monteiro, Local minima and convergence in low-rank semidefinite programming, Math. Program., 103 (2005), pp. 427--444.
5.
E. J. Candès, X. Li, Y. Ma, and J. Wright, Robust principal component analysis?, J. ACM, 58 (3) (2011), 11.
6.
E. J. Candès, T. Strohmer, and V. Voroninski, Phaselift: Exact and stable signal recovery from magnitude measurements via convex programming, Comm. Pure Appl. Math., 66 (2013), pp. 1241--1274.
7.
E. J. Candès and T. Tao, Near-optimal signal recovery from random projections: Universal encoding strategies, IEEE Trans. Inform. Theory, 52 (2006), pp. 5406--5425.
8.
C. Da Silva and F. J. Herrmann, Hierarchical Tucker tensor optimization: Applications to 4D seismic data interpolation, in 75th EAGE Conference & Exhibition Incorporating SPE EUROPEC 2013, 2013.
9.
L. Demanet, Curvelets, Wave Atoms, and Wave Equations, Ph.D. thesis, California Institute of Technology, 2006.
10.
D. Donoho, Compressed sensing, IEEE Trans. Inform. Theory, 52 (2006), pp. 1289--1306.
11.
M. Fazel, Matrix Rank Minimization with Applications, Ph.D. thesis, Stanford University, CA, 2002.
12.
M. A. T. Figueiredo, R. D. Nowak, and S. J. Wright, Gradient projection for sparse reconstruction: Application to compressed sensing and other inverse problems, IEEE J. Selected Topics Signal Process., 1 (2007), pp. 586 --597.
13.
M. Friedlander, H. Mansour, R. Saab, and O. Yilmaz, Recovering compressively sampled signals using partial support information, IEEE Trans. Inform. Theory, 58 (2012), pp. 1122--1134 .
14.
S. Funk, Netflix Update: Try This at Home, http://sifter.org/$\sim$simon/journal/20061211.html, 2006.
15.
R. Giryes, M. Elad, and Y. C. Eldar, The Projected GSURE for Automatic Parameter Tuning in Iterative Shrinkage Methods, preprint, CoRR, \burlalthttp://arxiv.org/abs/1003.3985abs/1003.3985 (2010).
16.
D. Gross, Recovering low-rank matrices from few coefficients in any basis, IEEE Trans. Inform. Theory, 57 (2011), pp. 1548--1566.
17.
F. J. Herrmann, M. P. Friedlander, and O. Yilmaz, Fighting the curse of dimensionality: Compressive sensing in exploration seismology, IEEE Signal Process. Mag., 29 (2012), pp. 88--100.
18.
F. J. Herrmann, M. P. Friedlander, and O. Yilmaz, Fighting the curse of dimensionality: Compressive sensing in exploration seismology, IEEE Signal Process. Mag., 29 (2012), pp. 88--100.
19.
F. J. Herrmann and G. Hennenfent, Non-parametric seismic data recovery with curvelet frames, Geophys. J. Internat., 173 (2008), pp. 233--248.
20.
P. J. Huber, Robust Statistics, Wiley, 1981.
21.
P. Jain, R. Meka, and I. Dhillon, Guaranteed rank minimization via singular value projection, in Advances in Neural Information Processing Systems 23 (NIPS 2010), J. Lafferty, C. K. I. Williams, J. Shawe-Taylor, R. S. Zemel, and A. Culotta, eds., 2010, pp. 937--945.
22.
P. Jain, P. Netrapalli, and S. Sanghavi, Low-rank matrix completion using alternating minimization, in Proceedings of the 45th Annual ACM Symposium on Theory of Computing (STOC '13), ACM, New York, 2013, pp. 665--674.
23.
K. L. Lange, R. J. A. Little, and J. M. G. Taylor, Robust statistical modeling using the $t$ distribution, J. Amer. Statist. Assoc., 84 (1989), pp. 881--896.
24.
J. Lee, B. Recht, R. Salakhutdinov, N. Srebro, and J. Tropp, Practical large-scale optimization for max-norm regularization, in Advances in Neural Information Processing Systems 23 (NIPS 2010), J. Lafferty, C. K. I. Williams, J. Shawe-Taylor, R. S. Zemel, and A. Culotta, eds., 2010, pp. 1297--1305.
25.
Z. Lin and S. Wei, A Block Lanczos with Warm Start Technique for Accelerating Nuclear Norm Minimization Algorithms, preprint, CoRR, http://arxiv.org/abs/1012.0365abs/1012.0365 (2010).
26.
J. Mairal, M. Elad, and G. Sapiro, Sparse representation for color image restoration, IEEE Trans. Image Process., 17 (2008), pp. 53--69.
27.
H. Mansour, F. J. Herrmann, and O. Yilmaz, Improved wavefield reconstruction from randomized sampling via weighted one-norm minimization, Geophysics, submitted (2012).
28.
H. Mansour, R. Saab, P. Nasiopoulos, and R. Ward, Color image desaturation using sparse reconstruction, in Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2010, pp. 778--781.
29.
H. Mansour, H. Wason, T. T. Y. Lin, and F. J. Herrmann, Randomized marine acquisition with compressive sampling matrices, Geophys. Prospecting, 60 (2012), pp. 648--662.
30.
R. A. Maronna, D. Martin, and Yohai, Robust Statistics, Wiley Series in Probability and Statistics, Wiley, 2006.
31.
R. Neelamani, C. E. Krohn, J. R. Krebs, J. K. Romberg, M. Deffenbaugh, and J. E. Anderson, Efficient seismic forward modeling using simultaneous random sources and sparsity, Geophys., 75 (2010), pp. WB15--WB27.
32.
V. Oropeza and M. Sacchi, Simultaneous seismic data denoising and reconstruction via multichannel singular spectrum analysis, Geophys., 76 (2011), pp. V25--V32.
33.
B. Recht, M. Fazel, and P. A. Parrilo, Guaranteed minimum-rank solutions of linear matrix equations via nuclear norm minimization, SIAM Rev., 52 (2010), pp. 471--501.
34.
B. Recht and C. Ré, Parallel stochastic gradient algorithms for large-scale matrix completion, Math. Program. Comput., 5 (2013), pp. 201--226.
35.
J. D. M. Rennie and N. Srebro, Fast maximum margin matrix factorization for collaborative prediction, in Proceedings of the 22nd International Conference on Machine Learning (ICML '05), 2005, pp. 713--719.
36.
R. T. Rockafellar and R. J.-B. Wets, Variational Analysis, Grundlehren Math. Wiss. 317, Springer, 1998.
37.
M. D. Sacchi, T. J. Ulrych, and C. J. Walker, Interpolation and extrapolation using a high-resolution discrete fourier transform, IEEE Trans. Signal Process., 46 (1998), pp. 31--38.
38.
J.-L. Starck, M. Elad, and D. Donoho, Image decomposition via the combination of sparse representation and a variational approach, IEEE Trans. Image Process., 14 (2005), pp. 1570--1582.
39.
E. van den Berg and M. P. Friedlander, Probing the Pareto frontier for basis pursuit solutions, SIAM J. Sci. Comput., 31 (2008), pp. 890--912.
40.
E. van den Berg and M. P. Friedlander, Sparse optimization with least-squares constraints, SIAM J. Optim., 21 (2011), pp. 1201--1229.
41.
B. Vandereycken, Low-rank matrix completion by Riemannian optimization, SIAM J. Optim., 23 (2013), pp. 1214--1236.
Information & Authors
Information
Published In
SIAM Journal on Scientific Computing
Pages: S237 - S266
DOI: 10.1137/130919210
ISSN (online): 1095-7197
Copyright
© 2014, Society for Industrial and Applied Mathematics.
History
Submitted: 1 May 2013
Accepted: 17 July 2014
Published online: 30 October 2014
Keywords
MSC codes
Authors
Metrics & Citations
Metrics
Citations
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.
Cited By
- Simultaneous seismic interpolation and statics estimation of land dataGEOPHYSICS, Vol. 90, No. 1 | 7 January 2025
- Fully invertible hyperbolic neural networks for segmenting large-scale surface and sub-surface dataArtificial Intelligence in Geosciences, Vol. 5 | 1 Dec 2024
- Seismic trace interpolation based on the principle of reciprocity using a conditional generative adversarial network (cGAN)Journal of Geophysics and Engineering, Vol. 21, No. 6 | 9 October 2024
- Uncertainty-Adjusted Recommendation via Matrix Factorization With Weighted LossesIEEE Transactions on Neural Networks and Learning Systems, Vol. 35, No. 11 | 1 Nov 2024
- HPETC: History Priority Enhanced Tensor Completion for Network Distance MeasurementIEEE Transactions on Parallel and Distributed Systems, Vol. 35, No. 6 | 1 Jun 2024
- Improving full-waveform inversion based on sparse regularization for geophysical dataJournal of Geophysics and Engineering, Vol. 21, No. 3 | 22 March 2024
- Improved full-waveform inversion based on sparse relaxed regularized regression processing of seismic dataSeventh International Conference on Engineering Geophysics, Al Ain, UAE, 16–19 October 2023 | 12 March 2024
- Low-rank-based residual statics estimation and correctionGEOPHYSICS, Vol. 88, No. 3 | 12 April 2023
- Spectral Gap-Based Seismic Survey DesignIEEE Transactions on Geoscience and Remote Sensing, Vol. 61 | 1 Jan 2023
- DTAE: Deep Tensor Autoencoder for 3-D Seismic Data InterpolationIEEE Transactions on Geoscience and Remote Sensing, Vol. 60 | 1 Jan 2022
- Multi-Weight Nuclear Norm Minimization for Low-Rank Matrix Recovery in Presence of Subspace Prior InformationIEEE Transactions on Signal Processing, Vol. 70 | 1 Jan 2022
- A practical workflow for land seismic wavefield recovery with weighted matrix factorizationFirst International Meeting for Applied Geoscience & Energy Expanded Abstracts | 1 September 2021
- Tubal-Sampling: Bridging Tensor and Matrix Completion in 3-D Seismic Data ReconstructionIEEE Transactions on Geoscience and Remote Sensing, Vol. 59, No. 1 | 1 Jan 2021
- Non-surface-consistent short-wavelength statics correction for dense and subsampled data: A rank-based approachSEG Technical Program Expanded Abstracts 2020 | 30 September 2020
- Seismic wavefield redatuming with regularized multi-dimensional deconvolutionInverse Problems, Vol. 36, No. 9 | 2 September 2020
- 2-D Seismic Data Reconstruction via Truncated Nuclear Norm RegularizationIEEE Transactions on Geoscience and Remote Sensing, Vol. 58, No. 9 | 1 Sep 2020
- A Unified Scalable Equivalent Formulation for Schatten Quasi-NormsMathematics, Vol. 8, No. 8 | 10 August 2020
- Regularized matrix completion with partial side informationNeurocomputing, Vol. 383 | 1 Mar 2020
- An Optimal Hybrid Nuclear Norm Regularization for Matrix Sensing With Subspace Prior InformationIEEE Access, Vol. 8 | 1 Jan 2020
- Basis Pursuit Denoise With Nonsmooth ConstraintsIEEE Transactions on Signal Processing, Vol. 67, No. 22 | 15 Nov 2019
- Seismic source reconstruction in an orthogonal geometry based on local and non-local information in the time slice domainJournal of Applied Geophysics, Vol. 170 | 1 Nov 2019
- Relaxation algorithms for matrix completion, with applications to seismic travel-time data interpolationInverse Problems, Vol. 35, No. 10 | 13 September 2019
- High-frequency wavefield recovery with weighted matrix factorizationsSEG Technical Program Expanded Abstracts 2019 | 10 August 2019
- Enabling numerically exact local solver for waveform inversion—a low-rank approachComputational Geosciences, Vol. 23, No. 4 | 27 June 2019
- Geostatistical interpolation of non-stationary seismic dataComputational Geosciences, Vol. 23, No. 4 | 18 March 2019
- Applications of low-rank compressed seismic data to full-waveform inversion and extended image volumesGEOPHYSICS, Vol. 84, No. 3 | 1 May 2019
- Simultaneous-shot inversion for PDE-constrained optimization problems with missing dataInverse Problems, Vol. 35, No. 2 | 27 December 2018
- Adapting Regularized Low-Rank Models for Parallel ArchitecturesSIAM Journal on Scientific Computing, Vol. 41, No. 1 | 3 January 2019
- A Unified Framework for Sparse Relaxed Regularized Regression: SR3IEEE Access, Vol. 7 | 1 Jan 2019
- Learning Tensors From Partial Binary MeasurementsIEEE Transactions on Signal Processing, Vol. 67, No. 1 | 1 Jan 2019
- A joint matrix minimization approach for seismic wavefield recoveryScientific Reports, Vol. 8, No. 1 | 1 February 2018
- Removing density effects in LSRTM with low-rank matched filterSEG Technical Program Expanded Abstracts 2018 | 27 August 2018
- Weighted Matrix Completion and Recovery With Prior Subspace InformationIEEE Transactions on Information Theory, Vol. 64, No. 6 | 1 Jun 2018
- Intelligent interpolation by Monte Carlo machine learningGEOPHYSICS, Vol. 83, No. 2 | 1 Mar 2018
- Massive 3D seismic data compression and inversion with hierarchical TuckerSEG Technical Program Expanded Abstracts 2017 | 17 August 2017
- Full-Waveform Inversion I Complete SessionSEG Technical Program Expanded Abstracts 2017 | 17 August 2017
- Highly repeatable 3D compressive full-azimuth towed-streamer time-lapse acquisition — A numerical feasibility study at scaleThe Leading Edge, Vol. 36, No. 8 | 1 Aug 2017
- Beating Level-Set Methods for 5-D Seismic Data Interpolation: A Primal-Dual Alternating ApproachIEEE Transactions on Computational Imaging, Vol. 3, No. 2 | 1 Jun 2017
- Five-Dimensional Seismic Reconstruction Using Parallel Square Matrix FactorizationIEEE Transactions on Geoscience and Remote Sensing, Vol. 55, No. 4 | 1 Apr 2017
- A fast rank-reduction algorithm for three-dimensional seismic data interpolationJournal of Applied Geophysics, Vol. 132 | 1 Sep 2016
- Dynamic matrix factorization with social influence2016 IEEE 26th International Workshop on Machine Learning for Signal Processing (MLSP) | 1 Sep 2016
- Fixed point algorithms for detection of parabolic eventsSEG Technical Program Expanded Abstracts 2016 | 1 September 2016
- Technical Program in full - Part II (RC 1 - VSP P1)SEG Technical Program Expanded Abstracts 2016 | 1 September 2016
- Seismic Modeling Complete SessionSEG Technical Program Expanded Abstracts 2016 | 1 September 2016
- Off-the-Grid Low-Rank Matrix Recovery and Seismic Data ReconstructionIEEE Journal of Selected Topics in Signal Processing, Vol. 10, No. 4 | 1 Jun 2016
- Multidimensional simultaneous random plus erratic noise attenuation and interpolation for seismic data by joint low-rank and sparse inversionGEOPHYSICS, Vol. 80, No. 6 | 1 Nov 2015
- Source separation for simultaneous towed-streamer marine acquisition — A compressed sensing approachGEOPHYSICS, Vol. 80, No. 6 | 1 Nov 2015
- Efficient matrix completion for seismic data reconstructionGEOPHYSICS, Vol. 80, No. 5 | 1 Sep 2015
- A new 5D seismic reconstruction method based on a Parallel Square Matrix Factorization algorithmSEG Technical Program Expanded Abstracts 2015 | 19 August 2015
- An Imaging Perspective of Low-Rank Seismic Data Interpolation and DenoisingSEG Technical Program Expanded Abstracts 2015 | 19 August 2015
- A variational formulation for interpolation of seismic traces with derivative informationInverse Problems, Vol. 31, No. 5 | 10 April 2015
View Options
- Access via your Institution
- Questions about how to access this content? Contact SIAM at [email protected].