Composite Convex Optimization with Global and Local Inexact Oracles

TL;DR

This paper develops new inexact oracle concepts for convex functions, enabling the design of advanced proximal Newton algorithms with proven convergence rates for a broad class of composite convex optimization problems.

Contribution

It introduces inexact second-order oracles for convex functions, expanding the class beyond standard self-concordant and Lipschitz gradient functions, and develops new algorithms with convergence guarantees.

Findings

New inexact second-order oracle framework for convex functions

Global convergence guarantees for proximal Newton-type schemes

Local convergence rates ranging from linear to quadratic

Abstract

We introduce new global and local inexact oracle concepts for a wide class of convex functions in composite convex minimization. Such inexact oracles naturally come from primal-dual framework, barrier smoothing, inexact computations of gradients and Hessian, and many other situations. We also provide examples showing that the class of convex functions equipped with the newly inexact second-order oracles is larger than standard self-concordant as well as Lipschitz gradient function classes. Further, we investigate several properties of convex and/or self-concordant functions under the inexact second-order oracles which are useful for algorithm development. Next, we apply our theory to develop inexact proximal Newton-type schemes for minimizing general composite convex minimization problems equipped with such inexact oracles. Our theoretical results consist of new optimization algorithms, accompanied with global convergence guarantees to solve a wide class of composite convex optimization problems. When the first objective term is additionally self-concordant, we establish different local convergence results for our method. In particular, we prove that depending on the choice of accuracy levels of the inexact second-order oracles, we obtain different local convergence rates ranging from $R$-linear and $R$-superlinear to $R$-quadratic. In special cases, where convergence bounds are known, our theory recovers the best known rates. We also apply our settings to derive a new primal-dual method for composite convex minimization problems. Finally, we present some representative numerical examples to illustrate the benefit of our new algorithms.