Finite-Time Convergence in Continuous-Time Optimization
Orlando Romero, Mouhacine Benosman
Abstract
In this paper, we propose two discontinuous dynamical systems in continuous time with guaranteed prescribed finite-time local convergence to strict local minima of a given cost function. Our approach consists of exploiting a Lyapunov-based differential inequality for differential inclusions, which leads to finite-time stability and thus finite-time convergence with a provable bound on the settling time. In particular, for exact solutions to the aforementioned differential inequality, the settling-time bound is also exact, thus achieving prescribed finite-time convergence. We thus construct a class of discontinuous dynamical systems, of second order with respect to the cost function, that serve as continuous-time optimization algorithms with finite-time convergence and prescribed convergence time. Finally, we illustrate our results on the Rosenbrock function.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Related papers
- Breaking the Convergence Barrier: Optimization via Fixed-Time Convergent FlowsParam Budhraja, Mayank Baranwal, Kunal Garg, Ashish R. HotaAAAI 2022 · 15 citations
- Neural Lyapunov Control for Discrete-Time SystemsJunlin Wu, Andrew Clark, Yiannis Kantaros, Yevgeniy VorobeychikNeurIPS 2023 · 61 citations
- Continuous-time Lower Bounds for Gradient-based AlgorithmsMichael Muehlebach, Michael I. JordanICML 2020 · 13 citations
- Global Convergence to Local Minmax Equilibrium in Classes of Nonconvex Zero-Sum GamesTanner Fiez, Lillian J. Ratliff, Eric Mazumdar, Evan Faulkner et al.NeurIPS 2021 · 29 citations
- How Deep Do We Need: Accelerating Training and Inference of Neural ODEs via Control PerspectiveKeyan Miao, Konstantinos GatsisICML 2024 · 2 citations
