A Composite Representation Theorem for Solution Mappings in Regularized Composite Optimization with Applications to Hausdorff Lipschitz Stability
Abstract
We study the geometry and stability of solution mappings in regularized composite optimization, allowing multiple minimizers. We establish a composite representation that separates optimal linear images from their corresponding primal solutions through an image mapping and a generalized basis pursuit mapping. Under a fiber-attainment condition, the image mapping admits a reduced optimization formulation; neither representation requires convexity. For convex regularizers, suitable qualification conditions yield a Fenchel-conjugate representation of the reduced value function and a geometric characterization of the generalized basis pursuit mapping through affine fibers and a fixed lifting set. Using these representations, we establish sufficient conditions for local Hausdorff Lipschitz continuity of possibly set-valued solution mappings. We further show that the primal-space sufficient conditions imply the corresponding image-space conditions, with an additional injectivity requirement arising in the former. The results cover ℓ1-type and structured piecewise linear-quadratic regularizers under suitable assumptions. For classical ℓ1 regularization, our approach recovers an existing stability result without a finite sign-pattern decomposition. Numerical examples illustrate the recovery of complete solution sets, including a case with a nonpolyhedral graph of the generalized basis pursuit mapping.
Related
- Regularized coordinate minimization for nonconvex composite optimization with application to quantized image compression
- Prior-Informed Generalizable Low-Rank Representation Learning via Regularized Adversarial Reweighting
- A Stochastic Proximal-Gradient Method for Regularized Generally Constrained Continuous Optimization
- A sequential regularized piecewise affine algorithm for nonconvex nonsmooth multicomposite optimization in RNN training
- Envelope Cubic Regularized Newton Method for Nonconvex-Strongly-Concave Minimax Optimization
BibTeX
@misc{yang2026composite,
title = {{A Composite Representation Theorem for Solution Mappings in Regularized Composite Optimization with Applications to Hausdorff Lipschitz Stability}},
author = {Peixuan Yang and Wei Yao and Jin Zhang},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.17105},
eprint = {2610.17105},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.17105},
}
RIS
TY - UNPB
TI - A Composite Representation Theorem for Solution Mappings in Regularized Composite Optimization with Applications to Hausdorff Lipschitz Stability
AU - Peixuan Yang
AU - Wei Yao
AU - Jin Zhang
PY - 2026
DA - 2026/10/12
PB - arXiv
DO - 10.48550/arxiv.2610.17105
UR - https://arxiv.org/abs/2610.17105
AB - We study the geometry and stability of solution mappings in regularized composite optimization, allowing multiple minimizers. We establish a composite representation that separates optimal linear images from their corresponding primal solutions through an image mapping and a generalized basis pursuit mapping. Under a fiber-attainment condition, the image mapping admits a reduced optimization formulation; neither representation requires convexity. For convex regularizers, suitable qualification conditions yield a Fenchel-conjugate representation of the reduced value function and a geometric characterization of the generalized basis pursuit mapping through affine fibers and a fixed lifting set. Using these representations, we establish sufficient conditions for local Hausdorff Lipschitz continuity of possibly set-valued solution mappings. We further show that the primal-space sufficient conditions imply the corresponding image-space conditions, with an additional injectivity requirement arising in the former. The results cover ℓ_1-type and structured piecewise linear-quadratic regularizers under suitable assumptions. For classical ℓ_1 regularization, our approach recovers an existing stability result without a finite sign-pattern decomposition. Numerical examples illustrate the recovery of complete solution sets, including a case with a nonpolyhedral graph of the generalized basis pursuit mapping.
ER -