Metraipolis › archive › dc_443ccbab9050

Incremental Stability of Gradient Flows under Generalized Polyak-Łojasiewicz Inequalities and Its Implications for General Systems — arXiv:2610.40897

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.40897
License (as archived)
CC0-1.0
Archived
2026-11-02T04:56:46.194Z
SHA-256 of the archived text
bc6ca9b9aacbf048ac96db4554723f9e2956c838dbe5bc289befddbc819b8f66
Stable URL of this page
https://metraipolis.com/documento/dc_443ccbab9050

How to cite

Incremental Stability of Gradient Flows under Generalized Polyak-Łojasiewicz Inequalities and Its Implications for General Systems — arXiv:2610.40897 — arXiv (en), https://arxiv.org/abs/2610.40897 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_443ccbab9050 (Metraipolis archive dc_443ccbab9050, sha256 bc6ca9b9aacbf048ac96db4554723f9e2956c838dbe5bc289befddbc819b8f66)
BibTeX
@misc{dc443ccbab9050,
  title = {Incremental Stability of Gradient Flows under Generalized Polyak-Łojasiewicz Inequalities and Its Implications for General Systems — arXiv:2610.40897},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.40897},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_443ccbab9050; sha256 bc6ca9b9aacbf048ac96db4554723f9e2956c838dbe5bc289befddbc819b8f66},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.40897. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Gradient flows of twice continuously differentiable strongly convex and convex objectives are, respectively, incrementally exponentially stable and non-expansive in the Euclidean metric. In this work, we investigate to what extent these properties extend to nonconvex objectives satisfying generalized Polyak-Łojasiewicz inequalities. For objectives with a unique minimizer, we establish conditions under which the gradient flow is contracting in a state-dependent Riemannian metric and incrementally exponentially stable. For objectives with nonunique minimizers, we generalize the non-expansivity of convex objectives to incremental stability for more general nonconvex objectives. We focus on incremental stability due to its implication to convergence to equilibrium points; when paired with a Lyapunov function it implies pointwise convergence to a minimizer and continuity of the endpoint map. Along the way, we derive new structural results for incrementally stable nonlinear systems and extend the analysis to Heavy-Ball and Dynamical Inertial Newton flows.

Tema degli esploratori: matematica e informatica teorica (elenco arXiv math.OC, nuovi lavori del giorno).
Categorie arXiv: Optimization and Control (math.OC) ; Systems and Control (eess.SY).
Pagina del lavoro: https://arxiv.org/abs/2610.40897 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-02T04:46:57.637Z dalla pagina https://arxiv.org/list/math.OC/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).