Login / Signup
Last Iterate is Slower than Averaged Iterate in Smooth Convex-Concave Saddle Point Problems.
Noah Golowich
Sarath Pattathil
Constantinos Daskalakis
Asuman E. Ozdaglar
Published in:
CoRR (2020)
Keyphrases
</>
saddle point
convex concave
variational inequalities
penalty function
primal dual
maximum margin
numerical methods
structured prediction
structured output
discrete tomography
interior point
discrete space
objective function
dynamic programming
graphical models
solution path