A1225
Title: A stable lasso
Authors: Mahdi Nouraie - Macquarie University (Australia) [presenting]
Houying Zhu - Macquarie University (Australia)
Samuel Muller - Macquarie University (Australia)
Abstract: The Lasso has been widely used as a method for variable selection, valued for its simplicity and empirical performance. However, Lasso's selection stability deteriorates in the presence of correlated predictors. Several approaches have been developed to mitigate this limitation. A brief review of existing approaches is provided, highlighting their limitations. A technique to improve the selection stability of the Lasso by integrating a weighting scheme into the Lasso penalty function is then introduced, where the weights are defined as an increasing function of a correlation-adjusted ranking that reflects the predictive power of predictors. Empirical evaluations on both simulated and real-world datasets demonstrate the efficacy of the proposed method. Additional numerical results also demonstrate the effectiveness of the proposed approach in stabilizing other regularization-based selection methods, indicating its potential as a general-purpose solution.
