A data-driven method designs probabilistic finite L2-gain stabilizers for stochastic linear systems from noisy trajectories via LMIs.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
LMI-Net enforces LMI constraints in neural networks by construction using a differentiable projection layer based on Douglas-Rachford splitting and implicit differentiation.
An iterative robust optimization framework jointly optimizes precoding, RIS reflection, common-rate allocation, and movable antenna positions to maximize sum-rate in multi-user RSMA systems under bounded CSI uncertainty.
citing papers explorer
-
Data-Driven Probabilistic Finite $\mathcal{L}_2$-Gain Stabilization of Stochastic Linear Systems
A data-driven method designs probabilistic finite L2-gain stabilizers for stochastic linear systems from noisy trajectories via LMIs.
-
LMI-Net: Linear Matrix Inequality--Constrained Neural Networks via Differentiable Projection Layers
LMI-Net enforces LMI constraints in neural networks by construction using a differentiable projection layer based on Douglas-Rachford splitting and implicit differentiation.
-
Channel Uncertainty-Aware Robust Beamforming for RIS-Assisted RSMA Communication With Movable Antennas
An iterative robust optimization framework jointly optimizes precoding, RIS reflection, common-rate allocation, and movable antenna positions to maximize sum-rate in multi-user RSMA systems under bounded CSI uncertainty.