AI & ML
Online Switching Control as Learning with Experts
arXiv eess.SY0 views
arXiv:2611.18352v1 Announce Type: cross Abstract: This paper addresses the problem of online switching control for discrete-time nonlinear systems where a controller is sequentially selected from a finite set of candidates. The goal is to generate an adaptive sequence of controllers to minimize the cumulative cost under unknown disturbances and cost functions. Specifically, we consider a full-information feedback setting where realized disturbance effects and cost functions are available after each selection. Using counterfactual costs computed from historical data, we reduce the online switching control problem to the experts problem with switching costs. Then, we propose an adaptive switching algorithm based on the Hedge algorithm with a switching suppression mechanism. Notably, the proposed algorithm achieves an expected regret of $O(\sqrt{T\log N})$, where $T$ is the time horizon and $N$ is the number of candidate controllers, while ensuring uniform boundedness of the state. This matches the optimal regret order for the standard experts problem.
Source:https://arxiv.org/abs/2611.18352PreviousSafety Certificates for Systems under Attack via Stackelberg Set GamesNextFrom AI-Enabled Remote Patient Monitoring Toward Agentic Robotics: Embodiment, Governance, and Care Integration
Related posts
Raw public keys move TLS identity into provisioning and rotation
0dev.to Security
External PSK importers make TLS key reuse a deployment decision
0dev.to Security

Why VirtIO Is Faster Than Emulated Devices: Virtqueues and vhost-net Explained
0dev.to Linux
HASHCAT
0dev.to Linux
Your dotfiles installer should be able to repair itself
0dev.to Linux
How to Build Trustworthy Enterprise AI: LLM Evaluation, Governance, and Risk Controls
0dev.to DevOps