Nonlinear Acceleration of Momentum and Primal-Dual Algorithms

Understand

We describe convergence acceleration schemes for multistep optimization algorithms.

• The extrapolated solution is written as a nonlinear average of the iterates produced by the original optimization method.
• Our analysis does not need the underlying fixed-point operator to be symmetric, hence handles e.g.
• algorithms with momentum terms such as Nesterov's accelerated method, or primal-dual methods.