Nonlinear Estimators and Tail Bounds for Dimension Reduction in l 1 Using Cauchy Random Projections

For 1 dimension reduction in l1, the method of Cauchy random projections multiplies the original data matrix A ∈ R with a random matrix R ∈ R (k ≪ min(n,D)) whose entries are i.i.d. samples of the standard Cauchy C(0, 1). Because of the impossibility results, one can not hope to recover the pairwise l1 distances in A from B = AR ∈ R, using linear estimators without incurring large errors. However, nonlinear estimators are still useful for certain applications in data stream computation, information retrieval, learning, and data mining. We propose three types of nonlinear estimators: the bias-corrected sample median estimator, the bias-corrected geometric mean estimator, and the bias-corrected maximum likelihood estimator. The sample median estimator and the geometric mean estimator are asymptotically (as k → ∞) equivalent but the latter is more accurate at small k. We derive explicit tail bounds for the geometric mean estimator and establish an analog of the Johnson-Lindenstrauss (JL) lemma for dimension reduction in l1, which is weaker than the classical JL lemma for dimension reduction in l2. Asymptotically, both the sample median estimator and the geometric mean estimators are about 80% efficient compared to the maximum likelihood estimator (MLE). We analyze the moments of the MLE and propose approximating the distribution of the MLE by an inverse Gaussian.