On-line Non-Convex Constrained Optimization
This addresses a fundamental problem in optimization for researchers and practitioners, but appears incremental as it builds on existing momentum and ODE methods.
The paper tackles the problem of time-varying non-convex constrained optimization by developing conditions for tracking local optima using a momentum-like regularizing term and an ODE approach, resulting in an efficient predictor-corrector algorithm.
Time-varying non-convex continuous-valued non-linear constrained optimization is a fundamental problem. We study conditions wherein a momentum-like regularising term allow for the tracking of local optima by considering an ordinary differential equation (ODE). We then derive an efficient algorithm based on a predictor-corrector method, to track the ODE solution.