An accelerated minimax algorithm for convex-concave saddle point problems with nonsmooth coupling function

Solving Nonconvex-Nonconcave Min-Max Problems exhibiting Weak Minty Solutions

“…Note that OGDA is most commonly written in the form where β = 1 is used, see [6,17,43], with the exception of two recent works which have investigated a more general coefficient see [45,55]. However, there, and for related methods [11,28,31], the parameter β is usually restricted to be less than 1. Only [55] allows for values larger than 1 and in their main theorem they actually use the same choice as we, namely β = 2.…”