Prox-NAG-GS: A Semi-Implicit Proximal Method for Composite Optimization
摘要
Composite optimization problems, where a smooth loss is combined with a nonsmooth regularizer, are common in machine learning and inverse problems. In this work, we study a proximal extension of NAG-GS, a semi-implicit accelerated method obtained from a Gauss-Seidel discretization of an inertial dynamics. The proposed method, called Prox-NAG-GS, keeps the coupled structure of NAG-GS for the smooth part and replaces the second update by a proximal step. It therefore applies to objectives of the form , where is smooth and is convex and proximable. We derive deterministic convergence guarantees for this method. The analysis has to account for a specific feature of the scheme. Prox-NAG-GS keeps two coupled sequences: an -sequence, on which the gradient of the smooth term is evaluated, and a -sequence, produced by the proximal update. The gradient is evaluated at , whereas the proximal step returns , which creates a mismatch absent from the standard proximal-gradient analysis. Under the sufficient condition that the proximal quadratic parameter is at least as large as the smoothness constant of , we control this mismatch through an augmented Lyapunov function involving both sequences. This gives a linear convergence result in the strongly convex composite case. In the convex case, the same Lyapunov structure yields an rate for the best iterate and for the averaged iterate. We test the method on deterministic Elastic Net and Group Lasso problems, and on stochastic sparse softmax-regression benchmarks. In the deterministic tests, Prox-NAG-GS reaches the same solutions as the baselines with substantially fewer iterations; for Group Lasso this also gives the best wall-clock time. In the stochastic tests, Prox-NAG-GS compares favorably with Prox-SGD in terms of data-fit reduction and gives similar test accuracies.
引用
@article{arxiv.2605.26260,
title = {Prox-NAG-GS: A Semi-Implicit Proximal Method for Composite Optimization},
author = {Sikeh Gisele Wiykiynyuy and Kelvin Asu Ekuri and Valentin Leplat},
journal= {arXiv preprint arXiv:2605.26260},
year = {2026}
}