Statistics – Machine Learning
Scientific paper
2007-06-04
IEEE Transactions on Information Theory, Volume 55, No.2, pp 846--866, 2009
Statistics
Machine Learning
59 pages, 5 figure, Submitted for review
Scientific paper
Recent research has studied the role of sparsity in high dimensional regression and signal reconstruction, establishing theoretical limits for recovering sparse models from sparse data. This line of work shows that $\ell_1$-regularized least squares regression can accurately estimate a sparse linear model from $n$ noisy examples in $p$ dimensions, even if $p$ is much larger than $n$. In this paper we study a variant of this problem where the original $n$ input variables are compressed by a random linear transformation to $m \ll n$ examples in $p$ dimensions, and establish conditions under which a sparse linear model can be successfully recovered from the compressed data. A primary motivation for this compression procedure is to anonymize the data and preserve privacy by revealing little information about the original data. We characterize the number of random projections that are required for $\ell_1$-regularized compressed regression to identify the nonzero coefficients in the true model with probability approaching one, a property called ``sparsistence.'' In addition, we show that $\ell_1$-regularized compressed regression asymptotically predicts as well as an oracle linear model, a property called ``persistence.'' Finally, we characterize the privacy properties of the compression procedure in information-theoretic terms, establishing upper bounds on the mutual information between the compressed and uncompressed data that decay to zero.
Lafferty John
Wasserman Larry
Zhou Shuheng
No associations
LandOfFree
Compressed Regression 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 Compressed Regression, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Compressed Regression will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-121302