Completion of Matrices with Low Description Complexity

by   Erwin Riegler, et al.
ETH Zurich
Austrian Academy of Sciences

We propose a theory for matrix completion that goes beyond the low-rank structure commonly considered in the literature and applies to general matrices of low description complexity, including sparse matrices, matrices with sparse factorizations such as, e.g., sparse R-factors in their QR-decomposition, and algebraic combinations of matrices of low description complexity. The mathematical concept underlying this theory is that of rectifiability, a basic notion in geometric measure theory. Complexity of the sets of matrices encompassed by the theory is measured in terms of Hausdorff and Minkowski dimensions. Our goal is the characterization of the number of linear measurements, with an emphasis on rank-1 measurements, needed for the existence of an algorithm that yields reconstruction, either perfect, with probability 1, or with arbitrarily small probability of error, depending on the setup. Specifically, we show that matrices taken from a set 𝒰 such that 𝒰-𝒰 has Hausdorff dimension s s-rectifiable) can be recovered from k>s measurements, and random matrices supported on a set 𝒰 of Hausdorff dimension s s-rectifiable set) can be recovered with probability 1 from k>s measurements. What is more, we establish the existence of β-Hölder continuous decoders recovering matrices taken from a set of upper Minkowski dimension s from k>2s/(1-β) measurements and, with arbitrarily small probability of error, random matrices supported on a set of upper Minkowski dimension s from k>s/(1-β) measurements.


page 1

page 2

page 3

page 4


Lossless Analog Compression

We establish the fundamental limits of lossless analog compression by co...

Compressed sensing of low-rank plus sparse matrices

Expressing a matrix as the sum of a low-rank matrix plus a sparse matrix...

Quantized Compressive Sensing with RIP Matrices: The Benefit of Dithering

In Compressive Sensing theory and its applications, quantization of sign...

A Unified Recovery of Structured Signals Using Atomic Norm

In many applications we seek to recover signals from linear measurements...

Consistent Collective Matrix Completion under Joint Low Rank Structure

We address the collective matrix completion problem of jointly recoverin...

Rank Minimization over Finite Fields: Fundamental Limits and Coding-Theoretic Interpretations

This paper establishes information-theoretic limits in estimating a fini...

Concentration of Random Feature Matrices in High-Dimensions

The spectra of random feature matrices provide essential information on ...

Please sign up or login with your details

Forgot password? Click here to reset