On the Resolution of Stochastic MPECs over Networks: Distributed Implicit Zeroth-Order Gradient Tracking Methods

TL;DR

This paper develops distributed zeroth-order gradient tracking methods for stochastic MPECs over networks, providing complexity guarantees and addressing both single-stage and two-stage problems with inexact solutions.

Contribution

It introduces novel distributed zeroth-order algorithms for SMPECs with theoretical complexity bounds, including the first inexact setting for two-stage problems.

Findings

Achieved the best-known complexity bound for centralized nonsmooth nonconvex stochastic optimization.

First to address inexact solutions in distributed two-stage SMPECs with complexity guarantees.

Improved dependence on dimension in complexity bounds for inexact single-stage SMPECs.

Abstract

The mathematical program with equilibrium constraints (MPEC) is a powerful yet challenging class of constrained optimization problems, where the constraints are characterized by a parametrized variational inequality (VI) problem. While efficient algorithms for addressing MPECs and their stochastic variants (SMPECs) have been recently presented, distributed SMPECs over networks pose significant challenges. This work aims to develop fully iterative methods with complexity guarantees for resolving distributed SMPECs in two problem settings: (1) distributed single-stage SMPECs and (2) distributed two-stage SMPECs. In both cases, the global objective function is distributed among a network of agents that communicate cooperatively. Under the assumption that the parametrized VI is uniquely solvable, the resulting implicit problem in upper-level decisions is generally neither convex nor smooth. Under some standard assumptions, including the uniqueness of the solution to the VI problems and the Lipschitz continuity of the implicit global objective function, we propose single-stage and two-stage zeroth-order distributed gradient tracking optimization methods where the gradient of a smoothed implicit objective function is approximated using two (possibly inexact) evaluations of the lower-level VI solutions. In the exact setting of both the single-stage and two-stage problems, we achieve the best-known complexity bound for centralized nonsmooth nonconvex stochastic optimization. This complexity bound is also achieved (for the first time) for our method in addressing the inexact setting of the distributed two-stage SMPEC. In addressing the inexact setting of the single-stage problem, we derive an overall complexity bound, improving the dependence on the dimension compared to the existing results for the centralized SMPECs.