The Łojasiewicz Inequality for Nonsmooth Subanalytic Functions with Applications to Subgradient Dynamical Systems III: Bounded Subgradient Trajectories Converge with Łojasiewicz RatesResearch Paper
Many optimization algorithms are discretizations of a continuous-time descent: the gradient flow for smooth objectives, and its nonsmooth analogue, the subgradient dynamical system, for objectives with kinks or constraints. A basic question about such a flow is whether a bounded trajectory actually converges, rather than merely…