arXiv · 2611.19683
Inequality-Constrained Optimization via Sliding Mode Control
Abstract
We present COSMIC (Constrained Optimization via Sliding Mode for Inequality Constraints), a continuous-time solver for inequality-constrained optimization. COSMIC couples primal gradient-flow dynamics with multiplier dynamics derived from sliding mode control laws on a manifold defined by the smoothed Fischer-Burmeister function. We prove that COSMIC's trajectories reach this manifold in finite time from any primal initial point, after which the dynamics reduces to the gradient flow of a logarithmic barrier function. This yields a control-theoretic interpretation of barrier methods while allowing infeasible initialization. For strongly convex problems, we further establish exponential convergence to the minimizer. To address the numerical stiffness that arises in discretization, we develop a modified discrete-time algorithm. We validate COSMIC across various machine learning applications, demonstrating its ability to solve optimization problems accurately while scaling effectively to high-dimensional settings.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Rawan Hoteit, Veronica Centorrino, Efe C. Balta, John Lygeros. 2026-11-15. Inequality-Constrained Optimization via Sliding Mode Control. https://searcharxiv.com/abs/2611.19683
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.