A Smooth Inexact Penalty Reformulation of Convex Problems with Linear Constraints

TL;DR

This paper introduces a smooth inexact penalty reformulation for convex problems with linear constraints, enabling efficient solution via gradient methods and ensuring solutions are feasible and near-optimal.

Contribution

It proposes a novel smooth penalty function approach with adjustable parameters, facilitating fast incremental gradient methods and a time-varying penalty scheme without needing problem-specific estimates.

Findings

Solutions are feasible and close to optimal with proper penalty parameters.

The method is suitable for large-scale problems with many constraints.

Convergence is proven for strongly convex objectives using time-varying penalties.

Abstract

In this work, we consider a constrained convex problem with linear inequalities and provide an inexact penalty re-formulation of the problem. The novelty is in the choice of the penalty functions, which are smooth and can induce a non-zero penalty over some points in feasible region of the original constrained problem. The resulting unconstrained penalized problem is parametrized by two penalty parameters which control the slope and the curvature of the penalty function. With a suitable selection of these penalty parameters, we show that the solutions of the resulting penalized unconstrained problem are \emph{feasible} for the original constrained problem, under some assumptions. Also, we establish that, with suitable choices of penalty parameters, the solutions of the penalized unconstrained problem can achieve a suboptimal value which is arbitrarily close to the optimal value of the original constrained problem. For the problems with a large number of linear inequality constraints, a particular advantage of such a smooth penalty-based reformulation is that it renders a penalized problem suitable for the implementation of fast incremental gradient methods, which require only one sample from the inequality constraints at each iteration. We consider applying SAGA proposed in \cite{saga} to solve the resulting penalized unconstrained problem. Moreover, we propose an alternative approach to set up the penalized problem. This approach is based on the time-varying penalty parameters and, thus, does not require knowledge about some problem-specific properties, that might be difficult to estimate. We prove that the single-loop full gradient-based algorithm applied to the corresponding time-varying penalized problem converges to the solution of the original constrained problem in the case of the strongly convex objective function.