Active Manifolds, Stratifications, and Convergence to Local Minima in Nonsmooth Optimization.

Saved in:
Bibliographic Details
Title: Active Manifolds, Stratifications, and Convergence to Local Minima in Nonsmooth Optimization.
Authors: Davis, Damek1 (AUTHOR), Drusvyatskiy, Dmitriy2 (AUTHOR) ddrusv@uw.edu, Jiang, Liwei1 (AUTHOR)
Source: Foundations of Computational Mathematics. Apr2026, Vol. 26 Issue 2, p779-861. 83p.
Subjects: Nonsmooth optimization, Subgradient methods, Stochastic processes, Lipschitz spaces, Submanifolds, Critical point theory
Abstract: In this work, we develop new regularity conditions in nonsmooth analysis that parallel the stratification conditions of Whitney, Kuo, and Verdier. They quantify how subgradients interact with a certain "active manifold" that captures the nonsmooth activity of the function. Based on these new conditions, we show that several subgradient-based methods converge only to local minimizers when applied to generic Lipschitz and subdifferentially regular functions that are definable in an o-minimal structure. At a high level, our argument is appealingly transparent: we interpret the nonsmooth dynamics as an approximate Riemannian gradient method on the active manifold. As a by-product, we extend the stochastic processes techniques of Pemantle. [ABSTRACT FROM AUTHOR]
Copyright of Foundations of Computational Mathematics is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
Full text is not displayed to guests.
FullText Links:
  – Type: pdflink
Text:
  Availability: 1
Header DbId: egs
DbLabel: Engineering Source
An: 193283912
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Active Manifolds, Stratifications, and Convergence to Local Minima in Nonsmooth Optimization.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Davis%2C+Damek%22">Davis, Damek</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Drusvyatskiy%2C+Dmitriy%22">Drusvyatskiy, Dmitriy</searchLink><relatesTo>2</relatesTo> (AUTHOR)<i> ddrusv@uw.edu</i><br /><searchLink fieldCode="AR" term="%22Jiang%2C+Liwei%22">Jiang, Liwei</searchLink><relatesTo>1</relatesTo> (AUTHOR)
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Foundations+of+Computational+Mathematics%22">Foundations of Computational Mathematics</searchLink>. Apr2026, Vol. 26 Issue 2, p779-861. 83p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Nonsmooth+optimization%22">Nonsmooth optimization</searchLink><br /><searchLink fieldCode="DE" term="%22Subgradient+methods%22">Subgradient methods</searchLink><br /><searchLink fieldCode="DE" term="%22Stochastic+processes%22">Stochastic processes</searchLink><br /><searchLink fieldCode="DE" term="%22Lipschitz+spaces%22">Lipschitz spaces</searchLink><br /><searchLink fieldCode="DE" term="%22Submanifolds%22">Submanifolds</searchLink><br /><searchLink fieldCode="DE" term="%22Critical+point+theory%22">Critical point theory</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: In this work, we develop new regularity conditions in nonsmooth analysis that parallel the stratification conditions of Whitney, Kuo, and Verdier. They quantify how subgradients interact with a certain "active manifold" that captures the nonsmooth activity of the function. Based on these new conditions, we show that several subgradient-based methods converge only to local minimizers when applied to generic Lipschitz and subdifferentially regular functions that are definable in an o-minimal structure. At a high level, our argument is appealingly transparent: we interpret the nonsmooth dynamics as an approximate Riemannian gradient method on the active manifold. As a by-product, we extend the stochastic processes techniques of Pemantle. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Foundations of Computational Mathematics is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=193283912
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1007/s10208-025-09691-0
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 83
        StartPage: 779
    Subjects:
      – SubjectFull: Nonsmooth optimization
        Type: general
      – SubjectFull: Subgradient methods
        Type: general
      – SubjectFull: Stochastic processes
        Type: general
      – SubjectFull: Lipschitz spaces
        Type: general
      – SubjectFull: Submanifolds
        Type: general
      – SubjectFull: Critical point theory
        Type: general
    Titles:
      – TitleFull: Active Manifolds, Stratifications, and Convergence to Local Minima in Nonsmooth Optimization.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Davis, Damek
      – PersonEntity:
          Name:
            NameFull: Drusvyatskiy, Dmitriy
      – PersonEntity:
          Name:
            NameFull: Jiang, Liwei
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 04
              Text: Apr2026
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-print
              Value: 16153375
          Numbering:
            – Type: volume
              Value: 26
            – Type: issue
              Value: 2
          Titles:
            – TitleFull: Foundations of Computational Mathematics
              Type: main
ResultId 1