On the primal-dual dynamics of Support Vector Machines
arXiv:1805.00699
Abstract
The aim of this paper is to study the convergence of the primal-dual dynamics pertaining to Support Vector Machines (SVM). The optimization routine, used for determining an SVM for classification, is first formulated as a dynamical system. The dynamical system is constructed such that its equilibrium point is the solution to the SVM optimization problem. It is then shown, using passivity theory, that the dynamical system is global asymptotically stable. In other words, the dynamical system converges onto the optimal solution asymptotically, irrespective of the initial condition. Simulations and computations are provided for corroboration.
To appear in MTNS 2018
Cited by in corpus (4)
- Beyond Convexity -- Contraction and Global Convergence of Gradient Descent
- Input-Output Performance of Linear-Quadratic Saddle-Point Algorithms with Application to Distributed Resource Allocation Problems
- Accelerated Distributed Primal-Dual Dynamics using Adaptive Synchronization
- Primal-Dual Gradient Flow Algorithm for Distributed Support Vector Machines