Statistical Inference of Constrained Stochastic Optimization via Sketched Sequential Quadratic Programming

arXiv:2205.13687v4 Announce Type: replace-cross
Abstract: We consider online statistical inference of constrained stochastic nonlinear optimization problems. We apply the Stochastic Sequential Quadratic Programming (StoSQP) method to solve these problems, which can be regarded as applying second-order Newton's method to the Karush-Kuhn-Tucker (KKT) conditions. In each iteration, the StoSQP method computes the Newton direction by solving a quadratic program, and then selects a proper adaptive stepsize $\bar{\alpha}_t$ to update the primal-dual iterate. To reduce dominant computational cost of the method, we …

abstract apply arxiv cs.lg inference iteration kkt math.oc optimization programming solve statistical stat.ml stochastic tucker type via