Continuous Relaxation of Discontinuous Shrinkage Operator: Proximal Inclusion and Conversion

Abstract

We present a principled way of deriving a continuous relaxation of a given discontinuous shrinkage operator, which is based on two fundamental results, proximal inclusion and conversion. Using our results, the discontinuous operator is converted, via double inversion, to a continuous operator; more precisely, the associated ``set-valued'' operator is converted to a ``single-valued'' Lipschitz continuous operator. The first illustrative example is the firm shrinkage operator which can be derived as a continuous relaxation of the hard shrinkage operator. We also derive a new operator as a continuous relaxation of the discontinuous shrinkage operator associated with the so-called reversely ordered weighted L1 (ROWL) penalty. Numerical examples demonstrate potential advantages of the continuous relaxation.

References in corpus (8)

• Nearly unbiased variable selection under minimax concave penalty
• Sparse Regularization via Convex Analysis
• Some sharp performance bounds for least squares regression with $L_1$ regularization
• Enhanced Low-Rank Matrix Approximation
• On the Convergence of the Iterative Shrinkage/Thresholding Algorithm With a Weakly Convex Penalty
• Linearly Involved Generalized Moreau Enhanced Models and Their Proximal Splitting Algorithm under Overall Convexity Condition
• Linearly-involved Moreau-Enhanced-over-Subspace Model: Debiased Sparse Modeling and Stable Outlier-Robust Regression
• A Unified Framework for Solving a General Class of Nonconvexly Regularized Convex Models

Cited by in corpus (1)

• Monotone Lipschitz-Gradient Denoiser: Explainability of Operator Regularization Approaches Free From Lipschitz Constant Control