# The achievable performance of convex demixing

arXiv: https://arxiv.org/abs/1309.7478 · HTML: https://mlsanity.com/paper/1309.7478/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Sep 2013.

## Built on by (most cited first, 1 of 1)

- [System Identification via Nuclear Norm Regularization](https://mlsanity.com/paper/2203.16673/) (2022)

## Abstract (arXiv)

Demixing is the problem of identifying multiple structured signals from a superimposed, undersampled, and noisy observation. This work analyzes a general framework, based on convex optimization, for solving demixing problems. When the constituent signals follow a generic incoherence model, this analysis leads to precise recovery guarantees. These results admit an attractive interpretation: each signal possesses an intrinsic degrees-of-freedom parameter, and demixing can succeed if and only if the dimension of the observation exceeds the total degrees of freedom present in the observation.