Stratification for Nonlinear Semidefinite Programming
Chenglong Bao, Chao Ding, Fuxiaoyue Feng, Jingyu Li

TL;DR
This paper develops a stratification framework for nonlinear semidefinite programming that enhances understanding of the geometry of the KKT system and proposes a globally convergent stratified Gauss-Newton algorithm.
Contribution
It introduces a novel stratification approach for NLSDP, linking geometric properties with regularity conditions and designing a new algorithm with proven convergence properties.
Findings
The stratified Gauss-Newton method converges globally to stationary points.
Under certain conditions, the method achieves local quadratic convergence.
The framework clarifies the geometric interpretation of regularity conditions.
Abstract
This paper introduces a stratification framework for nonlinear semidefinite programming (NLSDP) that reveals and utilizes the geometry behind the nonsmooth KKT system. Based on the \emph{index stratification} of and its lift to the primal--dual space, a stratified variational analysis is developed. Specifically, we define the stratum-restricted regularity property, characterize it by the verifiable weak second order condition (W-SOC) and weak strict Robinson constraint qualification (W-SRCQ), and interpret the W-SRCQ geometrically via transversality, which provides its genericity over ambient space and stability along strata. The interactions of these properties across neighboring strata are further examined, leading to the conclusion that classical strong-form regularity conditions correspond to the local uniform validity of stratum-restricted counterparts. On the…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Optimization Algorithms Research · Stochastic Gradient Optimization Techniques · Optimization and Variational Analysis
