5 papers · 1 filter
The Inexact Cyclic Block Proximal Gradient Method and Properties of Inexact Proximal Maps
Leandro Maia, David Huckleberry Gutman, Ryan Christopher Hughes
This paper expands the Cyclic Block Proximal Gradient method for block separable composite minimization by allowing for inexactly computed gradients and proximal maps. The resultan…
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…
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…
Enhanced Basic Procedures for the Projection and Rescaling Algorithm
David H. Gutman
Using an efficient algorithmic implementation of Caratheodory's theorem, we propose three enhanced versions of the Projection and Rescaling algorithm's basic procedures each of whi…
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…