Skip to content
DraconiticResearch
Search Sources API
203,234 studies31 sourcesUpdated 41 min ago
PreprintCC BY-NC-ND 4.0arXiv

BFGS can converge to non-Clarke-stationary points with positive probability

Abstract

We construct a coercive, locally Lipschitz, semialgebraic function on ℝ2 for which BFGS with Armijo--Wolfe line search converges to a non-Clarke-stationary point from a nonempty open set of initial points and inverse-Hessian estimates. This disproves the almost-sure stationarity assertion in the 2013 challenge of Lewis and Overton. The construction and proof combine analytical arguments with computer-assisted verification of explicit inequalities.

Related

  1. Bernstein type results for stationary points of variational integrals with subquadratic growth in two dimensions
    Michael Bildhauer, Martin Fuchs
    arXivPreprintCC BY 4.0Full textAnalysis & PDEsarXiv
  2. Random tilts to find stationary points in stochastic convex optimization
    Felipe Areces, John C. Duchi, Malo Sommers
    arXivPreprintarXiv licenceFull textOptimisation & controlStatisticsarXiv
  3. Second-Order Flows for Approaching Stationary Points via the SAV-E Approach
    Haifan Chen, Wei Liu, Ziqing Xie +1
    arXivPreprintarXiv licenceFull textNumerical analysis & scientific computingarXiv
  4. The Complexity of Finding Stationary Points in Nonsmooth Nonconvex Optimization
    Guy Kornowski
    arXivPreprintarXiv licenceFull textOptimisation & controlarXiv
  5. On the Complexity of Finding Stationary Points of p-th Order Hölder Smooth Functions in One Dimension
    Huanjian Zhou, Taiji Suzuki
    arXivPreprintCC BY 4.0Full textOptimisation & controlarXiv
BibTeX
@misc{lai2026bfgs,
  title = {{BFGS can converge to non-Clarke-stationary points with positive probability}},
  author = {Lexiao Lai},
  howpublished = {arXiv},
  year = {2026},
  month = oct,
  doi = {10.48550/arxiv.2610.34087},
  eprint = {2610.34087},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.34087},
  note = {CC BY-NC-ND 4.0},
}
RIS
TY  - UNPB
TI  - BFGS can converge to non-Clarke-stationary points with positive probability
AU  - Lexiao Lai
PY  - 2026
DA  - 2026/10/25
PB  - arXiv
DO  - 10.48550/arxiv.2610.34087
UR  - https://arxiv.org/abs/2610.34087
AB  - We construct a coercive, locally Lipschitz, semialgebraic function on ℝ^2 for which BFGS with Armijo--Wolfe line search converges to a non-Clarke-stationary point from a nonempty open set of initial points and inverse-Hessian estimates. This disproves the almost-sure stationarity assertion in the 2013 challenge of Lewis and Overton. The construction and proof combine analytical arguments with computer-assisted verification of explicit inequalities.
ER  -