Armijo backtracking variants are shown to achieve optimal first-order complexity under (L0,L1) smoothness and on analytic functions, with no hyperparameter tuning required.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
math.OC 1years
2024 1verdicts
REJECT 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Complexities of Armijo-like algorithms in Deep Learning context
Armijo backtracking variants are shown to achieve optimal first-order complexity under (L0,L1) smoothness and on analytic functions, with no hyperparameter tuning required.