Title: Efficient Algorithms for Minimizing a Class of Stochastic Nonconvex Optimization via (Implicit) Convex Reformulation
Abstract: We study a class of nonconvex stochastic optimization, where the objective function is a composition of a convex function and a random function. Leveraging an (implicit) convex reformulation via a variable transformation, we develop stochastic gradient-based algorithms and establish their sample and gradient complexities for achieving an $\epsilon$-global optimal solution. Interestingly, our proposed Mirror Stochastic Gradient (MSG) method operates only in the original decision space using gradient estimators of the original nonconvex objective and achieves $\tilde{\mathcal{O}}(\epsilon^{-2})$ sample and gradient complexities, which matches the lower bounds for solving stochastic convex optimization problems. Under booking limits control, we formulate the air-cargo network revenue management (NRM) problem with random two-dimensional capacity, random consumption, and routing flexibility as a special case of the stochastic nonconvex optimization, where the random demand truncates the booking limit decision. Extensive numerical experiments demonstrate the superior performance of our proposed MSG algorithm for booking limit control with higher revenue and lower computation cost than state-of-the-art bid-price-based control policies, especially when the variance of random capacity is large.