arXiv:2607. 11122v1 Announce Type: cross Abstract: Implicit neural controllers (INCs) are static feedback laws that are evaluated through an algebraic fixed point {equation}; they include as special cases neural network controllers.
arXiv:2404. 07373v2 Announce Type: replace-cross Abstract: This paper presents a method to synthesize neural network controllers to maximize reward subject to the hard constraint that the feedback system of plant and controller be dissipative, certifying requirements such as stability and $L_2$ gain bounds.
arXiv:2506. 01226v3 Announce Type: replace-cross Abstract: We study parameterizations of stabilizing nonlinear policies for learning-based control.
arXiv:2605. 08488v2 Announce Type: replace-cross Abstract: We develop a unified Lyapunov-integral quadratic constraint (IQC) framework for establishing uniform stability of first-order accelerated optimization algorithms in the $\beta$-smooth and $\gamma$-strongly convex regime.
arXiv:2609.22576v1 Announce Type: cross Abstract: Semidefinite programming (SDP) certificates for feedback systems containing deep neural networks (NNs) typically scale with the total number of neuro...
arXiv:2606. 09047v1 Announce Type: cross Abstract: A classical universal stabilization formula offers the practitioner no design freedom: it is a single, parameter-free object.
arXiv:2607. 01203v1 Announce Type: cross Abstract: This paper studies real-time robust optimal control for uncertain nonlinear systems, where linear time-varying (LTV) approximations make planning tractable but require sound linearization error bounds (LEBs) to guarantee robust constraint satisfaction.
arXiv:2606. 15271v1 Announce Type: cross Abstract: This work presents a transparent and reproducible benchmark study of a direct dual-network Physics-Informed Neural Network (PINN) formulation for the optimal control of a mass-spring-damper system.
arXiv:2408. 01273v3 Announce Type: replace Abstract: We propose a framework for training neural network controllers with certified robust forward invariant polytopes.
arXiv:2606. 30935v1 Announce Type: cross Abstract: While neural network control policies are powerful, their deployment on safety critical systems depends on ensuring that they obey strict constraints.
arXiv:2606. 12050v1 Announce Type: new Abstract: Physics-informed neural networks (PINNs) combine machine learning with physical laws to solve differential equations.
This paper presents a nonadaptive approach to robust nonlinear output regulation for general nonlinear systems with high relative degree in an output‑feedback setting. The design combines an input‑driven filter, a generic internal model, and a recursive backstepping law, transforming the regulation problem into robust input‑to‑state stabilization of an augmented error system. Under standard exosystem assumptions and a minimum‑phase input‑to‑state stability condition, the authors prove global asymptotic regulation and provide explicit inequalities for selecting design gains, demonstrating the method on a benchmark Duffing system.
arXiv:2608.24743v1 Announce Type: new Abstract: Existing linear program (LP) and semidefinite program (SDP) relaxations for rectified linear unit (ReLU) neural network (NN) verification yield overly-...