# Phase transitions for high-dimensional joint support recovery

Sahand NegahbanMartin J. Wainwright

We consider the following instance of transfer learning: given a pair of regression problems, suppose that the regression coefficients share a partially common support, parameterized by the overlap fraction $\overlap$ between the two supports. This set-up suggests the use of $1, \infty$-regularized linear regression for recovering the support sets of both regression vectors... (read more)

PDF Abstract