Compressed and Privacy-Sensitive Sparse Regression

Recent research has studied the role of sparsity in high-dimensional regression and signal reconstruction, establishing theoretical limits for recovering sparse models. This line of work shows that l(1)-regularized least squares regression can accurately estimate a sparse linear model from noisy examples in high dimensions. We study a variant of this problem where the original n input variables are compressed by a random linear transformation to m << 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 projections that are required for l(1)-regularized compressed regression to identify the nonzero coefficients in the true model with probability approaching one, a property called sparsistence. We also show that l(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, establishing upper bounds on the mutual information between the compressed and uncompressed data that decay to zero.