# Support recovery without incoherence: A case for nonconvex regularization

17 Dec 2014Po-Ling LohMartin J. Wainwright

We demonstrate that the primal-dual witness proof method may be used to establish variable selection consistency and $\ell_\infty$-bounds for sparse regression problems, even when the loss function and/or regularizer are nonconvex. Using this method, we derive two theorems concerning support recovery and $\ell_\infty$-guarantees for the regression estimator in a general setting... (read more)

PDF Abstract

No code implementations yet. Submit your code now