Skip to Main content Skip to Navigation
Preprints, Working Papers, ...

Inertial Newton Algorithms Avoiding Strict Saddle Points

Camille Castera 1
1 IRIT-SC - Signal et Communications
IRIT - Institut de recherche en informatique de Toulouse
Abstract : We study the asymptotic behavior of second-order algorithms mixing Newton's method and inertial gradient descent in non-convex landscapes. We show that, despite the Newtonian behavior of these methods, they almost always escape strict saddle points. We also evidence the role played by the hyper-parameters of these methods in their qualitative behavior near critical points. The theoretical results are supported by numerical illustrations.
Document type :
Preprints, Working Papers, ...
Complete list of metadata

https://hal-univ-tlse3.archives-ouvertes.fr/hal-03433202
Contributor : Camille Castera Connect in order to contact the contributor
Submitted on : Wednesday, November 17, 2021 - 4:08:08 PM
Last modification on : Friday, November 19, 2021 - 3:49:12 AM

File

2111.04596.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-03433202, version 1
  • ARXIV : 2111.04596

Citation

Camille Castera. Inertial Newton Algorithms Avoiding Strict Saddle Points. 2021. ⟨hal-03433202⟩

Share

Metrics

Les métriques sont temporairement indisponibles