Stochastic approximation method using diagonal positive-definite matrices for convex optimization with fixed point constraints

Abstract This paper proposes a stochastic approximation method for solving convex optimization problem over the fixed point set of quasinonexpansive mapping. The proposed is based on existing adaptive learning rate algorithms that use certain diagonal positive-definite matrices training deep neural networks. includes convergence analyses and under specific assumptions. Results show any accumulation sequence generated by with diminishing step-sizes almost surely belongs to solution in learning. Additionally, we apply methods classifier ensemble problems conduct numerical performance comparison showing achieve high accuracies faster than method.