RCML reformulates multiplier updating as projected-pressure feedback with residual tracking to improve stability and feasibility in stochastic constrained decision-making.
Stochastic smoot hed primal- dual algorithms for nonconvex optimization with linear ine quality constraints
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
A new Polyak-momentum augmented Lagrangian algorithm achieves O(ε^{-4}) stochastic gradient complexity for ε-stationary solutions in linearly constrained nonconvex problems under standard stochastic assumptions.
citing papers explorer
-
Residual-Controlled Multiplier Learning for Stochastic Constrained Decision-Making
RCML reformulates multiplier updating as projected-pressure feedback with residual tracking to improve stability and feasibility in stochastic constrained decision-making.