Provably data-driven projection method for quadratic programming
By: Anh Tuan Nguyen, Viet Anh Nguyen
Potential Business Impact:
Teaches computers to solve hard math problems faster.
Projection methods aim to reduce the dimensionality of the optimization instance, thereby improving the scalability of high-dimensional problems. Recently, Sakaue and Oki proposed a data-driven approach for linear programs (LPs), where the projection matrix is learned from observed problem instances drawn from an application-specific distribution of problems. We analyze the generalization guarantee for the data-driven projection matrix learning for convex quadratic programs (QPs). Unlike in LPs, the optimal solutions of convex QPs are not confined to the vertices of the feasible polyhedron, and this complicates the analysis of the optimal value function. To overcome this challenge, we demonstrate that the solutions of convex QPs can be localized within a feasible region corresponding to a special active set, utilizing Caratheodory's theorem. Building on such observation, we propose the unrolled active set method, which models the computation of the optimal value as a Goldberg-Jerrum (GJ) algorithm with bounded complexities, thereby establishing learning guarantees. We then further extend our analysis to other settings, including learning to match the optimal solution and input-aware setting, where we learn a mapping from QP problem instances to projection matrices.
Similar Papers
Data-driven Projection Generation for Efficiently Solving Heterogeneous Quadratic Programming Problems
Machine Learning (Stat)
Solves hard math problems much faster.
A projection-based framework for gradient-free and parallel learning
Machine Learning (CS)
Teaches computers new things without complex math.
A Geometric Approach to Problems in Optimization and Data Science
Optimization and Control
Makes computers learn better from messy or tricky information.