The phase transition of matrix recovery from Gaussian measurements matches the minimax MSE of matrix denoising
Open accessThe DOI matches its Crossref record.
Abstract
Let be an unknown M by N matrix. In matrix recovery, one takes linear measurements of , where and each is an M by N matrix. A popular approach for matrix recovery is nuclear norm minimization (NNM): solving the convex optimization problem for all , where denotes the nuclear norm, namely, the sum of singular values. Empirical work reveals a phase transition curve, stated in terms of the undersampling fraction , rank fraction , and aspect ratio . Specifically when the measurement matrices A i have independent standard Gaussian random entries, a curve exists such that, if , NNM typically succeeds for large M , N , whereas if , it typically fails. An apparently quite different problem is matrix denoising in Gaussian noise, in which an unknown M by N matrix is to be estimated based on direct noisy measurements , where the matrix Z has independent and identically distributed Gaussian entries. A popular matrix denoising scheme solves the unconstrained optimization problem . When optimally tuned, this scheme achieves the asymptotic minimax mean-squared error , where . We report extensive experiments showing that the phase transition in the first problem, matrix recovery from Gaussian measurements, coincides with the minimax risk curve in the second problem, matrix denoising in Gaussian noise: , for any rank fraction (at each common aspect ratio β). Our experiments considered matrices belonging to two constraint classes: real M by N matrices, of various ranks and aspect ratios, and real symmetric positive-semidefinite N by N matrices, of various ranks.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cited by
Weighted Nuclear Norm Minimization with Application to Image Denoising
Gu, S., Zhang, L., Zuo, W., & Feng, X. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.366 · Cited by 2,316
Living on the edge: phase transitions in convex programs with random data
Amelunxen, D., Lotz, M., McCoy, M. B., & Tropp, J. A. (2014) · Information and Inference · doi:10.1093/imaiai/iau005 · Cited by 413
On simplicity and complexity in the brave new world of large-scale neuroscience
Gao, P., & Ganguli, S. (2015) · Current Opinion in Neurobiology · doi:10.1016/j.conb.2015.04.003 · Cited by 405
Nonconvex Optimization Meets Low-Rank Matrix Factorization: An Overview
Chi, Y., Lu, Y. M., & Chen, Y. (2019) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2019.2937282 · Cited by 360
Complete Dictionary Recovery Over the Sphere I: Overview and the Geometric Picture
Sun, J., Qu, Q., & Wright, J. (2017) · IEEE Transactions on Information Theory · doi:10.1109/tit.2016.2632162 · Cited by 213
Metadata
- Authors
- Donoho, D. L., Gavish, M., & Montanari, A.
- Venue
- Proceedings of the National Academy of Sciences
- Published
- 2013-05-06
- Volume
- 110
- Issue
- 21
- Pages
- 8405-8410
- ISSN
- 0027-8424 (ISSN-L)
- 1091-6490
- OpenAlex
- W2119787772
- Cited by
- 57
- References
- 0
- FWCI
- 8.60
- Type
- journal article
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: The phase transition of matrix recovery from Gaussian measurements matches the minimax MSE of matrix denoising. https://app.cochat.ai/papers/10.1073/pnas.1306110110
- The paper
- Donoho, D. L., Gavish, M., & Montanari, A. (2013). The phase transition of matrix recovery from Gaussian measurements matches the minimax MSE of matrix denoising. Proceedings of the National Academy of Sciences. https://doi.org/10.1073/pnas.1306110110
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.