Tight Error Bounds for Nonnegative Orthogonality Constraints and Exact Penalties
For the intersection of the Stiefel manifold and the set of nonnegative matrices in ℝ^n× r, we present global and local error bounds with easily computable residual functions and explicit coefficients. Moreover, we show that the error bounds cannot be improved except for the coefficients, which explains why two square-root terms are necessary in the bounds when 1 < r < n for the nonnegativity and orthogonality, respectively. The error bounds are applied to penalty methods for minimizing a Lipschitz continuous function with nonnegative orthogonality constraints. Under only the Lipschitz continuity of the objective function, we prove the exactness of penalty problems that penalize the nonnegativity constraint, or the orthogonality constraint, or both constraints. Our results cover both global and local minimizers.
READ FULL TEXT