<ul><li>Researchers propose smoothed primal-dual algorithms for solving nonconvex optimization problems with linear inequality constraints.</li><li>The algorithms are single-loop and utilize one stochastic gradient based on one sample per iteration.</li><li>Estimation of the gradient of the Moreau envelope is performed using a stochastic primal-dual augmented Lagrangian method.</li><li>The algorithms provide optimal sample complexity guarantees for obtaining ɛ-stationary points and offer an improved complexity by using variance reduction and expected smoothness assumption.</li></ul>

Stochastic Smoothed Primal-Dual Algorithms for Nonconvex Optimization with Linear Inequality Constraints

Discover more