Answers are grounded in this paper and cite their sources.
To minimize or upper-bound the value of a function “robustly,” we might instead minimize or upper-bound the “ε-robust regularization,” defined as the map from a point to the maximum value of the function within an ε-radius. This regularization may be easy to compute: convex quadratics lead to semidefinite-representable regularizations, for example, and the spectral radius of a matrix leads to pseudospectral computations. For favorable classes of functions, we show that the robust regularization is Lipschitz around any given point, for all small ε>0, even if the original function is non-Lipschitz (like the spectral radius). One such favorable class consists of the semi-algebraic functions. Such functions have graphs that are finite unions of sets defined by finitely many polynomial inequalities, and are commonly encountered in applications.
No takes yet. Share an insight, caveat, or question.
Lewis et al. (2009) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: