Faster Stochastic Alternating Direction Method of Multipliers for Nonconvex Optimization
international conference on machine learning, 2019.
In this paper, we propose a faster stochastic alternating direction method of multipliers (ADMM) for nonconvex optimization by using a new stochastic path-integrated differential estimator (SPIDER), called as SPIDER-ADMM. Moreover, we prove that the SPIDER-ADMM achieves a record-breaking incremental first-order oracle (IFO) complexity o...More
PPT (Upload PPT)