Long term dynamics of the subgradient method for Lipschitz path differentiable functions
From MaRDI portal
Dynamical systems and their relations with probability theory and stochastic processes (37A50) Gradient-like behavior; isolated (locally maximal) invariant sets; attractors, repellers for topological dynamical systems (37B35) Neural nets and related approaches to inference from stochastic processes (62M45) Numerical optimization and variational techniques (65K10)
Abstract: We consider the long-term dynamics of the vanishing stepsize subgradient method in the case when the objective function is neither smooth nor convex. We assume that this function is locally Lipschitz and path differentiable, i.e., admits a chain rule. Our study departs from other works in the sense that we focus on the behavoir of the oscillations, and to do this we use closed measures. We recover known convergence results, establish new ones, and show a local principle of oscillation compensation for the velocities. Roughly speaking, the time average of gradients around one limit point vanishes. This allows us to further analyze the structure of oscillations, and establish their perpendicularity to the general drift.
This page was built for publication: Long term dynamics of the subgradient method for Lipschitz path differentiable functions
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6341713)
