A mixed-integer quadratically constrained optimization learns interpretable stable dynamical models and their Lyapunov functions from data by enforcing stability constraints during training.
Input convex neural networks
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
eess.SY 2verdicts
UNVERDICTED 2representative citing papers
InstructMPC uses an LLM plus tunable last layer to map operational context to disturbance trajectories for MPC, proving an O(sqrt(T log T)) regret bound for linear systems and showing lower grid costs on the OpenCEM microgrid.
citing papers explorer
-
Learning interpretable and stable dynamical models via mixed-integer Lyapunov-constrained optimization
A mixed-integer quadratically constrained optimization learns interpretable stable dynamical models and their Lyapunov functions from data by enforcing stability constraints during training.
-
Context-Aware Model Predictive Control for Microgrid Energy Management via LLMs
InstructMPC uses an LLM plus tunable last layer to map operational context to disturbance trajectories for MPC, proving an O(sqrt(T log T)) regret bound for linear systems and showing lower grid costs on the OpenCEM microgrid.