A1302
Title: Variable selection for high-dimensional regression models with higher-order interactions
Authors: Hsueh-Han Huang - Academia Sinica (Taiwan) [presenting]
Abstract: The network orthogonal greedy algorithm (network OGA) is proposed, an efficient method designed to capture higher-order (beyond second-order) interactions. By integrating the concepts of ranking and stepwise forward regression, network OGA leverages the advantages of both approaches. The algorithm is applicable to high-dimensional interaction models of arbitrary unknown orders. The sure screening property for network OGA is established and it is demonstrated that, when coupled with a high-dimensional information criterion (HDIC), the method achieves variable selection consistency. Simulation studies further validate its superior performance.
