Primal-dual adaptive and fast gradient methods with (δ, L)-models achieve optimal convergence rates for some optimization problems by solving approximated primal problems to recover dual solutions.
Lectures on modern convex optimization analysis, algorithms, and engineering applications
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Primal-dual fast gradient method with a model
Primal-dual adaptive and fast gradient methods with (δ, L)-models achieve optimal convergence rates for some optimization problems by solving approximated primal problems to recover dual solutions.