analiza aiqbench
This research introduces a Stein variational distributionally robust controller that couples optimal control with variational inference to handle latent parametric uncertainty in nonlinear dynamical systems. By focusing on parameter sensitivities critical to task objectives rather than relying on conservative worst-case assumptions, the method improves performance-robustness tradeoffs across various control problems without restrictive modeling constraints.
Stein Variational Uncertainty-Adaptive Model Predictive Control
arXiv:2604.01034v3 Announce Type: replace Abstract: We propose a Stein variational distributionally robust controller for nonlinear dynamical systems with latent parametric uncertainty. The method is an alternative to conservative worst-case ambiguity-set optimization with a deterministic particle-based approximation of a task-dependent uncertainty distribution, enabling the controller to concentrate on parameter sensitivities that most strongly affect closed-loop performance. Our method yields a controller that is robust to latent parameter uncertainty by coupling optimal control with Stein variational inference, and avoiding restrictive parametric assumptions on the uncertainty model while preserving computational parallelism. In contrast to classical DRO, which can sacrifice nominal performance through worst-case design, we find our approach achieves robustness by shaping the control law around relevant uncertainty that are most critical to the task objective. The proposed framework therefore reconciles robust control and variational inference in a single decision-theoretic formulation for broad classes of control systems with parameter uncertainty. We demonstrate our approach on representative control problems that empirically illustrate improved performance-robustness tradeoffs over nominal, ensemble, and classical distributionally robust baselines.
Abstract:We propose a Stein variational distributionally robust controller for nonlinear dynamical systems with latent parametric uncertainty. The method is an alternative to conservative worst-case ambiguity-set optimization with a deterministic particle-based approximation of a task-dependent uncertainty distribution, enabling the controller to concentrate on parameter sensitivities that most strongly affect closed-loop performance. Our method yields a controller that is robust to latent parameter uncertainty by coupling optimal control with Stein variational inference, and avoiding restrictive parametric assumptions on the uncertainty model while preserving computational parallelism. In contrast to classical DRO, which can sacrifice nominal performance through worst-case design, we find our approach achieves robustness by shaping the control law around relevant uncertainty that are most critical to the task objective. The proposed framework therefore reconciles robust control and variational inference in a single decision-theoretic formulation for broad classes of control systems with parameter uncertainty. We demonstrate our approach on representative control problems that empirically illustrate improved performance-robustness tradeoffs over nominal, ensemble, and classical distributionally robust baselines.
Robotics (cs.RO); Optimization and Control (math.OC)
arXiv:2604.01034 [cs.RO]
(or arXiv:2604.01034v3 [cs.RO] for this version)
Text integral sub licența deschisă a publicației · 178 cuvinte
Subiecte conexe
Adaptive Uncertainty-Aware Modeling and Stochastic Radial Basis Function Predictive Control for Personalized Fluid Resuscitation
arXiv · 21 sept. 2026
The Machines that Make the Machines
NVIDIA · 7 oct. 2026
Geometry-Aware Bayesian Parameter-Efficient Fine-Tuning on the Stiefel Manifold via Stein Variational Gradient Descent
arXiv · 9 sept. 2026
2026 BAIR Graduate Showcase
BAIR Blog · 1 iul. 2026