2022/09/13 by Ngoc Hoang Anh Mai, Mai, Ngoc Hoang Anh, Victor Magron +6
Computer Science · Mathematics · Physics and Astronomy · #Algebraic Geometry (math.AG) #FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (cs.LG) #Machine Learning and Algorithms #Model Reduction and Neural Networks #Optimization and Control (math.OC) #Tensor decomposition and applications
paper · doi:10.48550/arxiv.2209.06175
openalex publication_date 2022/09/13 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
We consider polynomial optimization problems (POP) on a semialgebraic set contained in the nonnegative orthant (every POP on a compact set can be put in this format by a simple translation of the origin). Such a POP can be converted to an equivalent POP by squaring each variable. Using even symmetry and the concept of factor width, we propose a hierarchy of semidefinite relaxations based on the extension of Pólya's Positivstellensatz by Dickinson-Povh. As its distinguishing and crucial feature, the maximal matrix size of each resulting semidefinite relaxation can be chosen arbitrarily and in addition, we prove that the sequence of values returned by the new hierarchy converges to the optimal value of the original POP at the rate O(ε-c) if the semialgebraic set has nonempty interior. When applied to (i) robustness certification of multi-layer neural networks and (ii) computation of positive maximal singular values, our method based on Pólya's Positivstellensatz provides better bounds and runs several hundred times faster than the standard Moment-SOS hierarchy.