Fréchet regression for multi-label feature selection with implicit regularization

Fr\'echet regression extends linear regression to model complex responses in metric spaces, making it particularly relevant for multi-label regression, where each instance can have multiple associated labels. However, variable selection within this framework remains underexplored. In this paper, we pro pose a novel variable selection method that employs implicit regularization instead of traditional explicit regularization approaches, which can introduce bias. Our method effectively captures nonlinear interactions between predic tors and responses while promoting model sparsity. We provide theoretical results demonstrating selection consistency and illustrate the performance of our approach through numerical examples

Implicit Regularization for Multi-label Feature Selection

In this paper, we address the problem of feature selection in the context of multi-label learning, by using a new estimator based on implicit regularization and label embedding. Unlike the sparse feature selection methods that use a penalized estimator with explicit regularization terms such as $l_{2,1}$-norm, MCP or SCAD, we propose a simple alternative method via Hadamard product parameterization. In order to guide the feature selection process, a latent semantic of multi-label information method is adopted, as a label embedding. Experimental results on some known benchmark datasets suggest that the proposed estimator suffers much less from extra bias, and may lead to benign overfitting.