Metraipolis › archive › dc_efdda21ff887

On the Absence of Identifiable Manifolds in Finite-Max Composite Optimization — arXiv:2608.16684

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.16684
License (as archived)
CC0-1.0
Archived
2026-10-18T20:19:09.420Z
SHA-256 of the archived text
7fe64af5f937e50be2cdf5322f714d5700b69355a173ec0596c50704487090a9
Stable URL of this page
https://metraipolis.com/documento/dc_efdda21ff887

How to cite

On the Absence of Identifiable Manifolds in Finite-Max Composite Optimization — arXiv:2608.16684 — arXiv (en), https://arxiv.org/abs/2608.16684 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_efdda21ff887 (Metraipolis archive dc_efdda21ff887, sha256 7fe64af5f937e50be2cdf5322f714d5700b69355a173ec0596c50704487090a9)
BibTeX
@misc{dcefdda21ff887,
  title = {On the Absence of Identifiable Manifolds in Finite-Max Composite Optimization — arXiv:2608.16684},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.16684},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_efdda21ff887; sha256 7fe64af5f937e50be2cdf5322f714d5700b69355a173ec0596c50704487090a9},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.16684. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

In nonsmooth optimization, identifiable sets describe the local region eventually reached by sequences converging to a prescribed critical point. When such a set is a $C^2$ manifold on which the objective restricts to a $C^2$ function, it is called an identifiable manifold. Their appeal lies in what they enable: many first-order methods identify these manifolds in finitely many iterations, after which the iterates enter a region in which the problem is effectively smooth. Consequently, many powerful tools and guarantees from smooth optimization transplant naturally to the nonsmooth setting. Owing to these properties, much existing work has focused on characterizing conditions that guarantee their existence. In this work, we study a complementary question: under what conditions is a critical point devoid of any identifiable manifold? We answer this by developing a deterministic branching criterion for a broad class of finite-max composite optimization problems, characterizing when a critical point admits no identifiable manifold. This criterion is surprisingly mild in certain classes of problems: it holds with high probability for overparameterized robust low-rank recovery and almost surely at common interpolators of random minimax regression, suggesting that the absence of identifiable manifolds may be the rule rather than the exception in modern optimization.

Tema degli esploratori: matematica e informatica teorica (retro-catalogo arXiv: annunci del 2026-08-18 in math.OC).
Categorie arXiv: Optimization and Control (math.OC).
Pagina del lavoro: https://arxiv.org/abs/2608.16684 — 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 2026-10-18T19:45:07.856Z dalla pagina https://arxiv.org/catchup/math.OC/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).