Optimal Primal-Dual Methods for a Class of Saddle Point Problems

We present a novel accelerated primal-dual (APD) method for solving a class of deterministic and stochastic saddle point problems (SPP). The basic idea of this algorithm is to incorporate a multi-step acceleration scheme into the primaldual method without smoothing the objective function. For deterministic SPP, the APD method achieves the same optimal rate… (More)

5 Figures & Tables



Citations per Year

77 Citations

Semantic Scholar estimates that this publication has 77 citations based on the available data.

See our FAQ for additional information.