Complete Dictionary Recovery Over the Sphere II: Recovery by Riemannian Trust-Region Method
Open accessThe DOI matches its Crossref record; 2 of the 2 references it cites were found in a registry or an index.
Abstract
We consider the problem of recovering a complete (i.e., square and invertible) matrix A0, from Y ∈ Rn×pwith Y = A0X0, provided X0is sufficiently sparse. This recovery problem is central to theoretical understanding of dictionary learning, which seeks a sparse representation for a collection of input signals and finds numerous applications in modern signal processing and machine learning. We give the first efficient algorithm that provably recovers A0when X0has O (n) nonzeros per column, under suitable probability model for X0. Our algorithmic pipeline centers around solving a certain nonconvex optimization problem with a spherical constraint, and hence is naturally phrased in the language of manifold optimization. In a companion paper, we have showed that with high probability, our nonconvex formulation has no “spurious” local minimizers and around any saddle point, the objective function has a negative directional curvature. In this paper, we take advantage of the particular geometric structure and describe a Riemannian trust region algorithm that provably converges to a local minimizer with from arbitrary initializations. Such minimizers give excellent approximations to the rows of X0. The rows are then recovered by a linear programming rounding and deflation.
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
Cites
Some NP-complete problems in quadratic and nonlinear programming
Murty, K. G., & Kabadi, S. N. (1987) · Mathematical Programming · doi:10.1007/bf02592948 · Cited by 1,003
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
Self-citation
Cited by
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
Global rates of convergence for nonconvex optimization on manifolds
Boumal, N., Absil, P.-A., & Cartis, C. (2019) · IMA Journal of Numerical Analysis · doi:10.1093/imanum/drx080 · Cited by 271
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
“These challenges are coupled, as function classes with known “good” analytic bases are rare.”
BackgroundMethodInfluentialSelf-citationRiemannian SVRG: Fast Stochastic Optimization on Riemannian Manifolds
Zhang, H., Reddi, S. J., & Sra, S. (2016) · arXiv · doi:10.48550/arxiv.1605.07147 · Cited by 140
“Many applications of Riemannian optimization are known, including matrix factorization on fixed-rank manifold [28; 30], dictionary learning [6; 27], optimization under orthogonality constraints [8; 18], learning elliptical distributions [26; 33], and Gaussian mixture models [11].”
Method
Metadata
- Authors
- Sun, J., Qu, Q., & Wright, J.
- Venue
- IEEE Transactions on Information Theory
- Published
- 2017-02
- Volume
- 63
- Issue
- 2
- Pages
- 885-914
- ISSN
- 0018-9448 (ISSN-L)
- 1557-9654
- OpenAlex
- W2255205876
- Cited by
- 112
- References
- 2
- FWCI
- 15.83
- 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.