A0674
Title: Robust sufficient dimension reduction and sufficient variable selection via distance covariance
Authors: Hsin-Hsiung Huang - University of Central Florida (United States)
Teng Zhang - University of Central Florida (United States) [presenting]
Abstract: Sufficient dimension reduction (SDR) using distance covariance (DCOV) was recently proposed as an approach to dimension-reduction problems. Compared with other SDR methods, it is model-free without estimating link function and does not require any particular distributions on predictors. However, the DCOV-based SDR method optimises a non-smooth and nonconvex objective function over the Stiefel manifold. To tackle the numerical challenge, the original objective function is equivalently formulated into a difference of convex functions program and develop an efficient algorithm based on the projection on the Stiefel manifold. In addition, the algorithm can also be readily extended to sufficient variable selection using distance covariance. Finally, the convergence property of the proposed algorithm under some regularity conditions is established. Simulation and real data analysis show the algorithm drastically improves the computation efficiency and is robust across various settings compared with the existing methods.
