A Proximal-Point Algorithm with Variable Sample-Sizes (PPAWSS) for Monotone Stochastic Variational Inequality Problems

We consider a stochastic variational inequality (SVI) problem with a continuous and monotone mapping over a closed and convex set. In strongly monotone regimes, we present a variable sample-size averaging scheme (VS-Ave) that achieves a linear rate with an optimal oracle complexity. In addition, the iteration complexity is shown to display a muted dependence on the condition number compared with standard variance-reduced projection schemes. To contend with merely monotone maps, we develop amongst the first proximal-point algorithms with variable sample-sizes (PPAWSS), where increasingly accurate solutions of strongly monotone SVIs are obtained via (VS-Ave) at every step. This allows for achieving a sublinear convergence rate that matches that obtained for deterministic monotone VIs. Preliminary numerical evidence suggests that the schemes compares well with competing schemes.

[1]  Alfredo N. Iusem,et al.  Extragradient Method with Variance Reduction for Stochastic Variational Inequalities , 2017, SIAM J. Optim..

[2]  A. Juditsky,et al.  Solving variational inequalities with Stochastic Mirror-Prox algorithm , 2008, 0809.0815.

[3]  P. Glynn,et al.  Smoothed Variable Sample-Size Accelerated Proximal Methods for Nonsmooth Stochastic Convex Programs , 2018, Stochastic Systems.

[4]  B. Hobbs,et al.  Variational Inequality Problems , 2013 .

[5]  Xiaoming Yuan,et al.  A Generalized Proximal Point Algorithm and Its Convergence Rate , 2014, SIAM J. Optim..

[6]  Alejandro Jofré,et al.  On variance reduction for stochastic smooth convex optimization with multiplicative noise , 2017, Math. Program..

[7]  Angelia Nedic,et al.  A regularized smoothing stochastic approximation (RSSA) algorithm for stochastic variational inequality problems , 2013, 2013 Winter Simulations Conference (WSC).

[8]  Houyuan Jiang,et al.  Stochastic Approximation Approaches to the Stochastic Variational Inequality Problem , 2008, IEEE Transactions on Automatic Control.

[9]  Anna Nagurney,et al.  Variational Inequalities , 2009, Encyclopedia of Optimization.

[10]  R. Rockafellar Monotone Operators and the Proximal Point Algorithm , 1976 .

[11]  Angelia Nedi'c,et al.  On Smoothing, Regularization and Averaging in Stochastic Approximation Methods for Stochastic Variational Inequalities , 2014, 1411.0209.

[12]  Yurii Nesterov,et al.  Solving Strongly Monotone Variational and Quasi-Variational Inequalities , 2006 .

[13]  F. Facchinei,et al.  Finite-Dimensional Variational Inequalities and Complementarity Problems , 2003 .

[14]  Saeed Ghadimi,et al.  Stochastic First- and Zeroth-Order Methods for Nonconvex Stochastic Programming , 2013, SIAM J. Optim..

[15]  Uday V. Shanbhag,et al.  Budget-constrained stochastic approximation , 2015, 2015 Winter Simulation Conference (WSC).

[16]  A. Iusem,et al.  FOR VARIATIONAL INEQUALITY PROBLEMS , 2010 .

[17]  Angelia Nedic,et al.  Regularized Iterative Stochastic Approximation Methods for Stochastic Variational Inequality Problems , 2013, IEEE Transactions on Automatic Control.