Two linesearch-based generalized conditional gradient methods, including a parameter-free variant from Ito et al., are proven to converge to stationary points without any Lipschitz or Hölder gradient assumption.
Complexity of linear min imization and projection on some sets
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2025 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
Convergence of linesearch-based generalized conditional gradient methods without smoothness assumptions
Two linesearch-based generalized conditional gradient methods, including a parameter-free variant from Ito et al., are proven to converge to stationary points without any Lipschitz or Hölder gradient assumption.