Dictionary Learning and Tensor Decomposition via the Sum-of-Squares Method

Abstract

We give a new approach to the dictionary learning (also known as "sparse coding") problem of recovering an unknown n x m matrix A (for m &#8805; n) from examples of the form [y = Ax + e,] where x is a random vector in R<sup>m</sup> with at most &#964; m nonzero coordinates, and e is a random noise vector in R<sup>n</sup> with bounded magnitude. For the case… (More)
DOI: 10.1145/2746539.2746605

Topics

1 Figure or Table

Statistics

010203020142015201620172018
Citations per Year

63 Citations

Semantic Scholar estimates that this publication has 63 citations based on the available data.

See our FAQ for additional information.

Blog articles referencing this paper

Slides referencing similar topics