arXiv subjects

Shiva Shakeri

Publications and source records attributed to Shiva Shakeri.

3 recordsLinked to original sources

arXiv2026

Hidden Star-Convexity in Policy Optimization for Gain-Scheduled LQR: Extended Version

We study policy optimization for gain-scheduled linear quadratic regulation, where one schedule of gains, interpolated through fixed weighting functions, is optimized against a family of plants. The resulting cost can develop spurious local minima, and existing convergence certificates are either local or severely conservative. We establish an exact identity: when the gradient of the cost is evaluated with the minimizer's closed-loop covariances, the scheduled cost is star-convex about the minimizer. The identity holds on the entire feasible set, for any parametrization of the schedule. Convergence is governed by a single dimensionless ratio. Wherever the ratio satisfies a threshold condition, gradient descent converges linearly to the optimum on entire sublevel regions at an explicit rate; at every spurious stationary point the condition necessarily fails. Experiments that maximize the ratio directly show the threshold to be an active boundary of the landscape. This extended version contains the complete proofs and additional numerical studies omitted from the letter for space.

math.OC↗

arXiv2026

Receding-Horizon Policy Gradient for Polytopic Controller Synthesis

We propose the Polytopic Receding-Horizon Policy Gradient (P-RHPG) algorithm for synthesizing Parallel Distributed Compensation (PDC) controllers via Tensor Product (TP) model transformation. Standard LMI-based PDC synthesis grows increasingly conservative as model fidelity improves; P-RHPG instead solves a finite-horizon integrated cost via backward-stage decomposition. The key result is that each stage subproblem is a strongly convex quadratic in the vertex gains, a consequence of the linear independence of the HOSVD weighting functions, guaranteeing a unique global minimizer and linear convergence of gradient descent from any initialization. With zero terminal cost, the optimal cost increases monotonically to a finite limit and the gain sequence remains bounded; terminal costs satisfying a mild Lyapunov condition yield non-increasing convergence. Experiments on an aeroelastic wing benchmark confirm convergence to a unique infinite-horizon optimum across all tested terminal cost choices and near-optimal performance relative to the pointwise Riccati lower bound.

eess.SY↗

arXiv2025

Robust Data-Driven Control for Nonlinear Systems Using their Digital Twins and Quadratic Funnels

This paper examines a robust data-driven approach for the safe deployment of systems with nonlinear dynamics using their imperfect digital twins. Our contribution involves proposing a method that fuses the digital twin's nominal trajectory with online, data-driven uncertainty quantification to synthesize robust tracking controllers. Specifically, we derive data-driven bounds to capture the deviations of the actual system from its prescribed nominal trajectory informed via its digital twin. Subsequently, the dataset is used in the synthesis of quadratic funnels -- robust positive invariant tubes around the nominal trajectory -- via linear matrix inequalities built on the time-series data. The resulting controller guarantees constraint satisfaction while adapting to the true system behavior through a segmented learning strategy, where each segment's controller is synthesized using uncertainty information from the previous segment. This work establishes a systematic framework for obtaining safety certificates in learning-based control of nonlinear systems with imperfect models.

eess.SY↗