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.
Stein variational gradient descent: A general purpose bayesian inference algorithm
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
A sampling-based safety filter using SV-MPC samples overrides unsafe nominal inputs and provides a probabilistic guarantee on restrictiveness via the scenario approach for collision avoidance.
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.
-
Sampling-Based Safety Filter with Probabilistic Restrictiveness Guarantee
A sampling-based safety filter using SV-MPC samples overrides unsafe nominal inputs and provides a probabilistic guarantee on restrictiveness via the scenario approach for collision avoidance.