Turnpike in Lipschitz-nonlinear optimal control

DOI10.1088/1361-6544/AC4E61zbMATH Open1484.49006arXiv2011.11091OpenAlexW4213299226MaRDI QIDQ5036285FDOQ5036285

Authors: Carlos Esteve-Yagüe, Borjan Geshkovski, Dario Pighin, Enrique Zuazua 

Publication date: 23 February 2022

Published in: Nonlinearity (Search for Journal in Brave)

Abstract: We present a new proof of the turnpike property for nonlinear optimal control problems, when the running target is a steady control-state pair of the underlying system. Our strategy combines the construction of quasi-turnpike controls via controllability, and a bootstrap argument, and does not rely on analyzing the optimality system or linearization techniques. This in turn allows us to address several optimal control problems for finite-dimensional, control-affine systems with globally Lipschitz (possibly nonsmooth) nonlinearities, without any smallness conditions on the initial data or the running target. These results are motivated by applications in machine learning through deep residual neural networks, which may be fit within our setting. We show that our methodology is applicable to controlled PDEs as well, such as the semilinear wave and heat equation with a globally Lipschitz nonlinearity, once again without any smallness assumptions.

Full work available at URL: https://arxiv.org/abs/2011.11091

Recommendations

• The turnpike property in nonlinear optimal control -- a geometric approach
• The turnpike property in semilinear control
• The turnpike property in finite-dimensional nonlinear optimal control
• A turnpike theorem for continuous-time control systems when the optimal stationary point is not unique
• Turnpike properties for partially uncontrollable systems

zbMATH Keywords

deep learningheat equationoptimal controlturnpike propertywave equationneural ODEsresnets

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Existence theories for optimal control problems involving relations other than differential equations (49J21)

Cites Work

• Understanding machine learning. From theory to algorithms
• Observation and control for operator semigroups
• Title not available (Why is that?)
• On the Existence of Positive Solutions of Semilinear Elliptic Equations
• Optimal Neumann control for the 1D wave equation: finite horizon, infinite horizon, boundary tracking terms and the turnpike property
• The turnpike property in finite-dimensional nonlinear optimal control
• Long time versus steady state optimal control
• Control and nonlinearity.
• Title not available (Why is that?)
• Exact controllability of semilinear plate equations
• Controllability and observability of partial differential equations: some results and open problems
• Title not available (Why is that?)
• Title not available (Why is that?)
• Exact Controllability for Multidimensional Semilinear Hyperbolic Equations
• Remarks on Long Time Versus Steady State Optimal Control
• Multiplicative controllability for semilinear reaction-diffusion equations with finitely many changes of sign
• A proposal on machine learning via dynamical systems
• A note on the semiglobal controllability of the semilinear wave equation
• Complexity of control-affine motion planning
• Null-controllability of perturbed porous medium gas flow
• Quadratic obstructions to small-time local controllability for scalar-input systems
• Controllability under positivity constraints of semilinear heat equations
• Turnpike property for two-dimensional Navier-Stokes equations
• Local controllability of reaction-diffusion systems around nonnegative stationary states
• Sensitivity analysis of optimal control for a class of parabolic PDEs motivated by model predictive control
• Exponential sensitivity and turnpike analysis for linear quadratic optimal control of general evolution equations
• Steady-State and Periodic Exponential Turnpike Property for Optimal Control Problems in Hilbert Spaces
• On the Turnpike Phenomenon for Optimal Boundary Control Problems with Hyperbolic Systems
• Control under constraints for multi-dimensional reaction-diffusion monostable and bistable equations
• A fragmentation phenomenon for a nonenergetic optimal control problem: optimization of the total population size in logistic diffusive models
• Controllability of one-dimensional viscous free boundary flows
• The turnpike property in semilinear control
• Optimal control of an energy-critical semilinear wave equation in 3D with spatially integrated control constraints
• Unexpected quadratic behaviors for the small-time local null controllability of scalar-input parabolic equations
• Hölder equivalence of the value function for control-affine systems
• Abstract nonlinear sensitivity and turnpike analysis and an application to semilinear parabolic PDEs

Cited In (11)

• Coupling by reflection for controlled diffusion processes: turnpike property and large time behavior of Hamilton-Jacobi-Bellman equations
• The turnpike property and the longtime behavior of the Hamilton-Jacobi-Bellman equation for finite-dimensional LQ control problems
• Sparsity in long-time control of neural ODEs
• The turnpike property in nonlinear optimal control -- a geometric approach
• Interpolation and approximation via momentum ResNets and neural ODEs
• Turnpike in optimal control of PDEs, ResNets, and beyond
• Quantitative Stability for Eigenvalues of Schrödinger Operator, Quantitative Bathtub Principle, and Application to the Turnpike Property for a Bilinear Optimal Control Problem
• Averaged turnpike property for differential equations with random constant coefficients
• A framework for randomized time-splitting in linear-quadratic optimal control
• Neural ODE Control for Classification, Approximation, and Transport
• Uniform turnpike property and singular limits

This page was built for publication: Turnpike in Lipschitz-nonlinear optimal control

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5036285)