A Nesterov-accelerated primal-dual gradient algorithm and its continuous-time analogue achieve O((1 - min{sqrt(mu_F/L_F), sqrt(mu_G/L_G)})^k) convergence for strongly convex-strongly concave bilinear saddle point problems.
USSR Comput
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
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Nesterov acceleration for strongly convex-strongly concave bilinear saddle point problems: discrete and continuous-time approaches
A Nesterov-accelerated primal-dual gradient algorithm and its continuous-time analogue achieve O((1 - min{sqrt(mu_F/L_F), sqrt(mu_G/L_G)})^k) convergence for strongly convex-strongly concave bilinear saddle point problems.