Regularized DDPC formulations are convex relaxations of bi-level identification-control problems, and the new A-DDPC algorithm outperforms prior regularized methods by lowering bias and variance errors.
Let δr σr+σp > 15 δ > 0 where σr is the induced p-norm of P2A† 3A2D† and σp is the constant such that∥v∥p ≤ σp∥v∥2 for any vector v with the same dimension of x1
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Regularization in Data-driven Predictive Control: A Convex Relaxation Perspective
Regularized DDPC formulations are convex relaxations of bi-level identification-control problems, and the new A-DDPC algorithm outperforms prior regularized methods by lowering bias and variance errors.