Enregistré dans:
Détails bibliographiques
Auteurs principaux: Chen, Xingxiao, Cannon, Mark
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:https://arxiv.org/abs/2605.14846
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866911685736923136
author Chen, Xingxiao
Cannon, Mark
author_facet Chen, Xingxiao
Cannon, Mark
contents We propose a data-driven Model Predictive Control (MPC) framework that employs a transformer encoder to generate multi-step predictions. To handle the nonconvex attention mechanism, we derive difference of convex (DC) representations of the transformer encoder components and embed them in a successive convex programming (SCP) iteration. Recursive feasibility and convergence of the SCP iterates are guaranteed, and each iterate yields a solution estimate satisfying the problem constraints. Under mild assumptions, the SCP iteration converges to a locally optimal solution of the MPC problem. The approach is illustrated on a benchmark nonlinear control problem.
format Preprint
id arxiv_https___arxiv_org_abs_2605_14846
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Successive convex optimization for transformer encoder model predictive control
Chen, Xingxiao
Cannon, Mark
Optimization and Control
We propose a data-driven Model Predictive Control (MPC) framework that employs a transformer encoder to generate multi-step predictions. To handle the nonconvex attention mechanism, we derive difference of convex (DC) representations of the transformer encoder components and embed them in a successive convex programming (SCP) iteration. Recursive feasibility and convergence of the SCP iterates are guaranteed, and each iterate yields a solution estimate satisfying the problem constraints. Under mild assumptions, the SCP iteration converges to a locally optimal solution of the MPC problem. The approach is illustrated on a benchmark nonlinear control problem.
title Successive convex optimization for transformer encoder model predictive control
topic Optimization and Control
url https://arxiv.org/abs/2605.14846