A Sequential Quadratic Programming Method with High Probability Complexity Bounds for Nonlinear Equality Constrained Stochastic Optimization

Understand

A step-search sequential quadratic programming method is proposed for solving nonlinear equality constrained stochastic optimization problems.

• It is assumed that constraint function values and derivatives are available, but only stochastic approximations of the objective function and its associated derivatives can be computed via inexact probabilistic zeroth- and first-order oracles.
• Under reasonable assumptions, a high-probability bound on the iteration complexity of the algorithm to approximate first-order stationarity is derived.
• Numerical results on standard nonlinear optimization test problems illustrate the advantages and limitations of our proposed method.