Mallows-type model averaging: Non-asymptotic analysis and all-subset combination

Model averaging (MA) and ensembling play a crucial role in statistical and machine learning practice. When multiple candidate models are considered, MA techniques can be used to weight and combine them, often resulting in improved predictive accuracy and better estimation stability compared to model selection (MS) methods. In this paper, we address two important problems in combining least squares estimators from both theoretical and practical perspectives. We first establish several oracle inequalities for least squares MA via minimizing a Mallows' Cp criterion under an arbitrary candidate model set. Compared to existing studies, these oracle inequalities yield faster excess risk and directly imply the asymptotic optimality of the resulting MA estimators under milder conditions. Moreover, we consider candidate model construction and investigate the problem of optimal all-subset combination for least squares estimators, which remains an important yet not fully understood topic in the existing literature. We show that there exists a fundamental limit to achieving the optimal all-subset MA risk. To attain this limit, we propose a novel Mallows-type MA procedure based on a dimension-adaptive Cp criterion. The implicit ensembling effects of several MS procedures are also revealed and discussed. We conduct several numerical experiments to support our theoretical findings and demonstrate the effectiveness of the proposed Mallows-type MA estimator.