Proposes single-stage and two-stage distributed implicit zeroth-order gradient tracking methods for stochastic MPECs over networks that achieve best-known complexity bounds for centralized nonsmooth nonconvex stochastic optimization under uniqueness and Lipschitz assumptions.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
math.OC 3representative citing papers
κ-distributed LQR controllers achieve performance exponentially close to the centralized optimum under stabilizability, detectability, and subexponential graph growth.
Sensitivity of primal-dual solutions in graph-induced NLPs decays exponentially with graph distance under SOSC and LICQ.
citing papers explorer
-
On the Resolution of Stochastic MPECs over Networks: Distributed Implicit Zeroth-Order Gradient Tracking Methods
Proposes single-stage and two-stage distributed implicit zeroth-order gradient tracking methods for stochastic MPECs over networks that achieve best-known complexity bounds for centralized nonsmooth nonconvex stochastic optimization under uniqueness and Lipschitz assumptions.
-
Near-Optimal Distributed Linear-Quadratic Regulator for Networked Systems
κ-distributed LQR controllers achieve performance exponentially close to the centralized optimum under stabilizability, detectability, and subexponential graph growth.
-
Exponential Decay of Sensitivity in Graph-Structured Nonlinear Programs
Sensitivity of primal-dual solutions in graph-induced NLPs decays exponentially with graph distance under SOSC and LICQ.