Approximate Dual Averaging Method for Multiagent Saddle-Point Problems with Stochastic Subgradients
نویسندگان
چکیده
منابع مشابه
SADDLE POINT VARIATIONAL METHOD FOR DIRAC CONFINEMENT
A saddle point variational (SPV ) method was applied to the Dirac equation as an example of a fully relativistic equation with both negative and positive energy solutions. The effect of the negative energy states was mitigated by maximizing the energy with respect to a relevant parameter while at the same time minimizing it with respect to another parameter in the wave function. The Cornell pot...
متن کاملAn Eecient Stochastic Approximation Algorithm for Stochastic Saddle Point Problems
We show that Polyak's (1990) stochastic approximation algorithm with averaging originally developed for unconstrained minimization of a smooth strongly convex objective function observed with noise can be naturally modiied to solve convex-concave stochas-tic saddle point problems. We also show that the extended algorithm, considered on general families of stochastic convex-concave saddle point ...
متن کاملAn Implicit Approximate Inverse Preconditioner for Saddle Point Problems
We present a preconditioner for saddle point problems which is based on an approximation of an implicit representation of the inverse of the saddle point matrix. Whereas this preconditioner does not require an approximation to the Schur complement, its theoretical analysis yields some interesting relationship to some Schurcomplement-based preconditioners. Whereas the evaluation of this new prec...
متن کاملAn interior point method for constrained saddle point problems
We present an algorithm for the constrained saddle point problem with a convexconcave function L and convex sets with nonempty interior. The method consists of moving away from the current iterate by choosing certain perturbed vectors. The values of gradients of L at these vectors provide an appropriate direction. Bregman functions allow us to define a curve which starts at the current iterate ...
متن کاملAdaptive Primal-dual Hybrid Gradient Methods for Saddle-point Problems
The Primal-Dual hybrid gradient (PDHG) method is a powerful optimization scheme that breaks complex problems into simple sub-steps. Unfortunately, PDHG methods require the user to choose stepsize parameters, and the speed of convergence is highly sensitive to this choice. We introduce new adaptive PDHG schemes that automatically tune the stepsize parameters for fast convergence without user inp...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Mathematical Problems in Engineering
سال: 2014
ISSN: 1024-123X,1563-5147
DOI: 10.1155/2014/202737