Finding Dantzig selectors with a proximity operator based fixed-point algorithm
This is an incremental improvement for researchers and practitioners in statistics and machine learning needing faster Dantzig selector computations.
The paper tackled the problem of efficiently computing the Dantzig selector for linear regression by proposing a fixed-point algorithm, resulting in a method that produces similar quality results as an alternating direction method but is significantly faster.
In this paper, we study a simple iterative method for finding the Dantzig selector, which was designed for linear regression problems. The method consists of two main stages. The first stage is to approximate the Dantzig selector through a fixed-point formulation of solutions to the Dantzig selector problem. The second stage is to construct a new estimator by regressing data onto the support of the approximated Dantzig selector. We compare our method to an alternating direction method, and present the results of numerical simulations using both the proposed method and the alternating direction method on synthetic and real data sets. The numerical simulations demonstrate that the two methods produce results of similar quality, however the proposed method tends to be significantly faster.