تقرير
Near-optimal Closed-loop Method via Lyapunov Damping for Convex Optimization
العنوان: | Near-optimal Closed-loop Method via Lyapunov Damping for Convex Optimization |
---|---|
المؤلفون: | Maier, Severin, Castera, Camille, Ochs, Peter |
سنة النشر: | 2023 |
المجموعة: | Computer Science Mathematics |
مصطلحات موضوعية: | Mathematics - Optimization and Control, Computer Science - Machine Learning, Mathematics - Dynamical Systems |
الوصف: | We introduce an autonomous system with closed-loop damping for first-order convex optimization. While, to this day, optimal rates of convergence are almost exclusively achieved by non-autonomous methods via open-loop damping (e.g., Nesterov's algorithm), we show that our system, featuring a closed-loop damping, exhibits a rate arbitrarily close to the optimal one. We do so by coupling the damping and the speed of convergence of the system via a well-chosen Lyapunov function. By discretizing our system we then derive an algorithm and present numerical experiments supporting our theoretical findings. |
نوع الوثيقة: | Working Paper |
الوصول الحر: | http://arxiv.org/abs/2311.10053Test |
رقم الانضمام: | edsarx.2311.10053 |
قاعدة البيانات: | arXiv |
الوصف غير متاح. |