Proves that QPOC problems have a benign landscape with all critical points being global optima or strict saddles, and shows the population and large-sample HePPCA inherit this with local geodesic strong concavity.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Benign Landscape of Quadratic Programs with Orthogonality Constraints and Its Application to Heteroscedastic Probabilistic PCA
Proves that QPOC problems have a benign landscape with all critical points being global optima or strict saddles, and shows the population and large-sample HePPCA inherit this with local geodesic strong concavity.