Efficient Algorithms for Minimizing Compositions of Convex Functions and Random Functions and Its Applications in Network Revenue Management

68 Pages Posted: 6 May 2022

See all articles by Xin Chen

Xin Chen

University of Illinois at Urbana-Champaign

ETH Zurich

Yifan Hu

University of Illinois at Urbana-Champaign

Zikun Ye

University of Illinois at Urbana-Champaign

Date Written: May 3, 2022

Abstract

In this paper, 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.

Keywords: stochastic nonconvex optimization, hidden convexity, air-cargo network revenue management, gradient-based algorithms

Suggested Citation

Chen, Xin and He, Niao and Hu, Yifan and Ye, Zikun, Efficient Algorithms for Minimizing Compositions of Convex Functions and Random Functions and Its Applications in Network Revenue Management (May 3, 2022). Available at SSRN: https://ssrn.com/abstract=4099814 or http://dx.doi.org/10.2139/ssrn.4099814