A distributionally robust PAC-Bayesian approach derives sub-Gaussian loss proxies and performance bounds tied to closed-loop operator norms via system level synthesis, enabling optimization-based safety certificates for controllers facing sim-to-real gaps.
Vershynin,High-dimensional probability: An introduction with applications in data science
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
New epoch-based direct MRAC algorithm for adaptive discrete-time LQR achieves high-probability regret bounds without requiring an initial stabilizing controller or exploration.
Multitask LQG control via history-dependent lifting to LQR yields generalization bounds tied to bisimulation heterogeneity and reduces policy gradient variance proportionally to the number of training tasks.
citing papers explorer
-
Distributionally Robust PAC-Bayesian Control
A distributionally robust PAC-Bayesian approach derives sub-Gaussian loss proxies and performance bounds tied to closed-loop operator norms via system level synthesis, enabling optimization-based safety certificates for controllers facing sim-to-real gaps.
-
Adapt and Stabilize, Then Learn and Optimize: A New Approach to Adaptive LQR
New epoch-based direct MRAC algorithm for adaptive discrete-time LQR achieves high-probability regret bounds without requiring an initial stabilizing controller or exploration.
-
Multitask LQG Control: Performance and Generalization Bounds
Multitask LQG control via history-dependent lifting to LQR yields generalization bounds tied to bisimulation heterogeneity and reduces policy gradient variance proportionally to the number of training tasks.