Mathematics – Statistics Theory
Scientific paper
2011-12-02
Mathematics
Statistics Theory
19 pages, 3 figures. Partial of this work is presented at NIPS 2011 conference in Granda, Spain, December 2011
Scientific paper
This paper studies the problem of accurately recovering a sparse vector $\beta^{\star}$ from highly corrupted linear measurements $y = X \beta^{\star} + e^{\star} + w$ where $e^{\star}$ is a sparse error vector whose nonzero entries may be unbounded and $w$ is a bounded noise. We propose a so-called extended Lasso optimization which takes into consideration sparse prior information of both $\beta^{\star}$ and $e^{\star}$. Our first result shows that the extended Lasso can faithfully recover both the regression as well as the corruption vector. Our analysis relies on the notion of extended restricted eigenvalue for the design matrix $X$. Our second set of results applies to a general class of Gaussian design matrix $X$ with i.i.d rows $\oper N(0, \Sigma)$, for which we can establish a surprising result: the extended Lasso can recover exact signed supports of both $\beta^{\star}$ and $e^{\star}$ from only $\Omega(k \log p \log n)$ observations, even when the fraction of corruption is arbitrarily close to one. Our analysis also shows that this amount of observations required to achieve exact signed support is indeed optimal.
Nguyen Nam H.
Tran Trac D.
No associations
LandOfFree
Robust Lasso with missing and grossly corrupted observations does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Robust Lasso with missing and grossly corrupted observations, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Robust Lasso with missing and grossly corrupted observations will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-139830