3 papers
math.OC2019
Coordinate Descent Without Coordinates: Tangent Subspace Descent on Riemannian Manifolds
David Huckleberry Gutman, Nam Ho-Nguyen
We extend coordinate descent to manifold domains, and provide convergence analyses for geodesically convex and non-convex smooth objective functions. Our key insight is to draw an…
math.OC2019
The condition number of a function relative to a set
David H. Gutman, Javier F. Pena
The condition number of a differentiable convex function, namely the ratio of its smoothness to strong convexity constants, is closely tied to fundamental properties of the functio…
math.OC2018
Convergence rates of proximal gradient methods via the convex conjugate
David H. Gutman, Javier F. Pena
We give a novel proof of the and convergence rates of the proximal gradient and accelerated proximal gradient methods for composite convex minimization. The cru…