The DOI matches its Crossref record; 2 of the 2 references it cites were found in a registry or an index.
Optimal Shrinkage of Singular Values
Open accessAbstract
We consider the recovery of low-rank matrices from noisy data by shrinkage of singular values, in which a single, univariate nonlinearity is applied to each of the empirical singular values. We adopt an asymptotic framework, in which the matrix size is much larger than the rank of the signal matrix to be recovered, and the signal-to-noise ratio of the low-rank piece stays constant. For a variety of loss functions, including Mean Square Error (MSE) - (square Frobenius norm), the nuclear norm loss and the operator norm loss, we show that in this framework there is a well-defined asymptotic loss that we evaluate precisely in each case. In fact, each of the loss functions we study admits a unique admissible shrinkage nonlinearity dominating all other nonlinearities. We provide a general method for evaluating these optimal nonlinearities, and demonstrate our framework by working out simple, explicit formulas for the optimal nonlinearities in the Frobenius, nuclear and operator norm cases. For example, for a square low-rank n-by-n matrix observed in white noise with level σ, the optimal nonlinearity for MSE loss simply shrinks each data singular value y to √(y2-4nσ2) (or to 0 if y2, which compares favorably with optimally tuned hard thresholding and optimally tuned soft thresholding, providing guarantees of 3nrσ2and 6nrσ2, respectively. Our general method also allows one to evaluate optimal shrinkers numerically to arbitrary precision. As an example, we compute optimal shrinkers for the Schatten-p norm loss, for any p > 0.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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
Cites
The Scree Test For The Number Of Factors
Cattell, R. B. (1966) · Multivariate Behavioral Research · doi:10.1207/s15327906mbr0102_10 · Cited by 13,554
Principal components analysis corrects for stratification in genome-wide association studies
Price, A. L., Patterson, N. J., Plenge, R. M., Weinblatt, M. E., Shadick, N. A., & Reich, D. (2006) · Nature Genetics · doi:10.1038/ng1847 · Cited by 10,248
Cited by
The Optimal Hard Threshold for Singular Values is \(4/\sqrt {3}\)
Gavish, M., & Donoho, D. L. (2014) · IEEE Transactions on Information Theory · doi:10.1109/tit.2014.2323359 · Cited by 675
Self-citationInferring biological networks by sparse identification of nonlinear dynamics
Mangan, N. M., Brunton, S. L., Proctor, J. L., & Kutz, J. N. (2016) · IEEE Transactions on Molecular, Biological and Multi-Scale Communications · doi:10.1109/tmbmc.2016.2633265 · Cited by 436
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
Complex diffusion-weighted image estimation via matrix recovery under general noise models
Cordero-Grande, L., Christiaens, D., Hutter, J., Price, A. N., & Hajnal, J. V. (2019) · NeuroImage · doi:10.1016/j.neuroimage.2019.06.039 · Cited by 354
Bidimensional linked matrix factorization for pan-omics pan-cancer analysis
Lock, E. F., Park, J. Y., & Hoadley, K. A. (2022) · The Annals of Applied Statistics · doi:10.1214/21-aoas1495 · Cited by 19
Metadata
- Authors
- Gavish, M., & Donoho, D. L.
- Venue
- IEEE Transactions on Information Theory
- Published
- 2017-04
- Volume
- 63
- Issue
- 4
- Pages
- 2137-2152
- ISSN
- 0018-9448 (ISSN-L)
- 1557-9654
- OpenAlex
- W2158044763
- Cited by
- 193
- References
- 2
- FWCI
- 9.92
- 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
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.