4 papers
Learning Universal Costs via Multi-Observation Inverse Optimal Transport
Chenglong Bao, Zanyu Li, Defeng Sun
Classical Inverse Optimal Transport (IOT) typically infers a cost function from a single observed transport plan, which may be sensitive to noise and observational biases in practi…
Stratification for Nonlinear Semidefinite Programming
Chenglong Bao, Chao Ding, Fuxiaoyue Feng +1
This paper introduces a stratification framework for nonlinear semidefinite programming (NLSDP) that reveals and utilizes the geometry behind the nonsmooth KKT system. Based on the…
Well-Posedness and Efficient Algorithms for Inverse Optimal Transport with Bregman Regularization
Chenglong Bao, Zanyu Li, Yunan Yang
This work analyzes the inverse optimal transport (IOT) problem under Bregman regularization. We establish well-posedness results, including existence, uniqueness (up to equivalence…
A Regularized Newton Method for Nonconvex Optimization with Global and Local Complexity Guarantees
Yuhao Zhou, Jintao Xu, Bingrui Li +3
Finding an -stationary point of a nonconvex function with a Lipschitz continuous Hessian is a central problem in optimization. Regularized Newton methods are a classical tool an…