Robust LassoNet: Enhancing Feature Selection in Neural Networks via Robust Loss Functions

Excerpt

arXiv:2609.38263v1 Announce Type: cross Abstract: Feature selection in neural networks remains a challenging problem, particularly in the presence of noisy or contaminated data. LassoNet is a recent approach that addresses this issue by combining neural networks with hierarchical sparsity constraints, enabling simultaneous prediction and variable selection. However, its standard formulation relies on the mean squared error (MSE) loss, which is known to be highly sensitive to outliers. In this pa