Regret Minimization in Stochastic Non-Convex Learning via a Proximal-Gradient Approach

Motivated by applications in machine learning and operations research, we study regret minimization with stochastic first-order oracle feedback in online constrained, and possibly non-smooth, non-convex problems. In this setting, the minimization of external regret is beyond reach, so we focus on a local regret measures defined via a proximal-gradient residual mapping. To achieve no (local) … Read more