DIPPA: An improved Method for Bilinear Saddle Point Problems

This paper studies bilinear saddle point problems $\min_{\bf{x}} \max_{\bf{y}} g(\bf{x}) + \bf{x}^{\top} \bf{A} \bf{y} - h(\bf{y})$, where the functions $g,h$ are smooth and strongly-convex. When the gradient and proximal oracle related to $g$ and $h$ are accessible, optimal algorithms have already been developed in the literature \cite{chambolle2011first, palaniappan2016stochastic}. However, the proximal operator is not always easy to compute, especially in constraint zero-sum matrix games \cite{zhang2020sparsified}. This work proposes a new algorithm which only requires the access to the gradients of $g,h$. Our algorithm achieves a complexity upper bound $\tilde{$\mathcal{O}$}\left( \frac{|\bf{A}|_2}{\sqrt{\mu_x \mu_y}} + \sqrt[4]{\kappa_x \kappa_y (\kappa_x

• \kappa_y)} \right)$ which has optimal dependency on the coupling condition number $\frac{\mathrm{\parallel }\mathbf{A}{\mathbf{\parallel }}_{\mathbf{2}}}{\sqrt{{\mu }_x{\mu }_y}}$ up to logarithmic factors.