Answers are grounded in this paper and cite their sources.
Demonstrates linear convergence of minimization methods on smooth manifolds, indicating improved optimization techniques.
It is proved that any strongly convex Lipschitz differentiable function satisfies the Polyak–Lojasiewicz condition on a proximally smooth C1-smooth manifold under a certain relationship between the proximal smoothness constant of the manifold and strong convexity constant of the function. This condition guarantees a linear convergence rate of the gradient projection method for minimizing the function on the manifold. An algorithm for finding a metric projection of a point located sufficiently close to a manifold onto this manifold is proposed.
No takes yet. Share an insight, caveat, or question.
M. V. Balashov (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: