Stochastic DCA for minimizing a large sum of DC functions with application to multi-class logistic regression

We consider the large sum of DC (Difference of Convex) functions minimization problem which appear in several different areas, especially in stochastic optimization and machine learning. Two DCA (DC Algorithm) based algorithms are proposed: stochastic DCA and inexact stochastic DCA. We prove that the convergence of both algorithms to a critical point is guaranteed with probability one. Furthermore, we develop our stochastic DCA for solving an important problem in multi-task learning, namely group variables selection in multi class logistic regression. The corresponding stochastic DCA is very inexpensive, all computations are explicit. Numerical experiments on several benchmark datasets and synthetic datasets illustrate the efficiency of our algorithms and their superiority over existing methods, with respect to classification accuracy, sparsity of solution as well as running time. •The large sum of Difference of Convex functions minimization problem is considered.•Two DC algorithms are proposed: stochastic DCA and inexact stochastic DCA.•We prove that both algorithms converge with probability one to a critical point.•Application on group variables selection in multi class logistic regression is considered.•Numerical experiments on several synthetic and benchmark datasets are performed.