AI RESEARCH
A Unified Fractional Regularization Framework for Sparse Recovery
arXiv CS.LG
•
ArXi:2604.23184v1 Announce Type: cross We propose a unified fractional regularization framework for sparse signal recovery based on the $\ell_1/\ell_p^q$ model. Our main theoretical contribution is the characterization of the equivalence between the first-order stationary points of the $\ell_1/\ell_p^q$ formulation and the subtractive $\ell_1 - \alpha \ell_p$ model, providing a unified perspective on these nonconvex regularizers.