Turnpike in optimal control of PDEs, ResNets, and beyond

DOI10.1017/S0962492922000046WikidataQ114116566 ScholiaQ114116566MaRDI QIDQ5887835

Borjan Geshkovski, Enrique Zuazua

Publication date: 14 April 2023

Published in: Acta Numerica (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2202.04097

Mathematics Subject Classification ID

Fluid mechanics (76-XX) Numerical analysis (65-XX)

Related Items (5)

Sparsity in long-time control of neural ODEs ⋮ Turnpike properties for partially uncontrollable systems ⋮ Neural ODE Control for Classification, Approximation, and Transport ⋮ Uniform turnpike property and singular limits ⋮ Coupling by reflection for controlled diffusion processes: turnpike property and large time behavior of Hamilton-Jacobi-Bellman equations

Uses Software

• SOCS
• MNIST
• ImageNet
• FFJORD

Cites Work

• On the relation between strict dissipativity and turnpike properties
• Optimal observability of the multi-dimensional wave and Schrödinger equations in quantum ergodic domains
• From averaged to simultaneous controllability
• Greedy controllability of finite dimensional linear systems
• The turnpike property in finite-dimensional nonlinear optimal control
• On representation formulas for long run averaging optimal control problem
• Direct and indirect methods for trajectory optimization
• On the relation between turnpike properties and dissipativity for continuous time linear quadratic optimal control problems
• Controllability issues for continuous-spectrum systems and ensemble controllability of Bloch equations
• Mean field games
• Aerodynamic design via control theory
• Optimal control on an infinite time horizon
• Model predictive control: Theory and practice - a survey
• Further results on controllability of recurrent neural networks
• Complete controllability of continuous-time recurrent neural networks
• Integral and measure-turnpike properties for infinite-dimensional optimal control systems
• Greedy optimal control for elliptic problems and its application to turnpike problems
• Local exact controllability of the Navier-Stokes system
• Turnpike property for two-dimensional Navier-Stokes equations
• Exact controllability for semilinear wave equations in one space dimension
• Optimal control and applications to aerospace: some results and challenges
• Long time average of mean field games
• Controllability under positivity constraints of semilinear heat equations
• Selection dynamics for deep neural networks
• On the turnpike property with interior decay for optimal control problems
• Pace and motor control optimization for a runner
• Observability results related to fractional Schrödinger operators
• The turnpike property and the longtime behavior of the Hamilton-Jacobi-Bellman equation for finite-dimensional LQ control problems
• On the nonuniqueness and instability of solutions of tracking-type optimal control problems
• Interpolation and approximation via momentum ResNets and neural ODEs
• On the sample complexity of the linear quadratic regulator
• The mean field Schrödinger problem: ergodic behavior, entropy estimates and functional inequalities
• Shape turnpike for linear parabolic PDE models
• Control under constraints for multi-dimensional reaction-diffusion monostable and bistable equations
• An introduction to mean field game theory
• Controllability and positivity constraints in population dynamics with age structuring and diffusion
• Characterization by observability inequalities of controllability and stabilization properties
• Deep learning as optimal control problems: models and numerical methods
• Exponential sensitivity and turnpike analysis for linear quadratic optimal control of general evolution equations
• Controllability under positivity constraints of multi-d wave equations
• Optimal shape and location of sensors for parabolic equations with random initial data
• Turnpike theory of continuous-time linear optimal control problems
• Turnpike results for discrete-time optimal control systems arising in economic dynamics
• Nonlinear model predictive control. Theory and algorithms
• Greedy algorithms for reduced bases in Banach spaces
• A proposal on machine learning via dynamical systems
• On turnpike and dissipativity properties of continuous-time optimal control problems
• On the relation between turnpike properties for finite and infinite horizon optimal control problems
• Long time behavior of the master equation in mean field game theory
• Null controllability of Grushin-type operators in dimension two
• Approximation and learning by greedy algorithms
• Asymptotic solutions for large time of Hamilton-Jacobi equations in Euclidean \(n\) space
• Dissipative dynamical systems. I: General theory
• Wave propagation, observation and control in 1-\(d\) flexible multi-structures.
• Control on the manifolds of mappings with a view to the deep learning
• Numerical aspects of large-time optimal control of Burgers equation
• Ensemble controllability by Lie algebraic methods
• Long Time Average of Mean Field Games with a Nonlocal Coupling
• Inverse problems: A Bayesian perspective
• Multidisciplinary Optimization with Applications to Sonic-Boom Minimization
• Hölder equivalence of the value function for control-affine systems
• Exact Boundary Controllability of 1-D Parabolic and Hyperbolic Degenerate Equations
• Complexity of Control-Affine Motion Planning
• Invariance of the Reachable Set under Nonlinear Perturbations
• Long Time Behavior of a Two-Phase Optimal Design for the Heat Equation
• Transient Wave Imaging with Limited-View Data
• On the Existence of a Limit Value in Some Nonexpansive Optimal Control Problems
• An Exponential Turnpike Theorem for Dissipative Discrete Time Optimal Control Problems
• State-constrained controllability of linear reaction-diffusion systems
• Long time behavior and turnpike solutions in mildly non-monotone mean field games
• Asymptotic solutions of Hamilton-Jacobi equations in Euclidean $n$ space
• Numerical solution of saddle point problems
• Lagrange Multiplier Approach to Variational Problems and Applications
• Stabilization of the Wave Equation on 1-d Networks
• Numerical approximation of null controls for the heat equation: Ill-posedness and remedies
• Practical Methods for Optimal Control and Estimation Using Nonlinear Programming
• Exact Controllability, Stabilization and Perturbations for Distributed Systems
• Sharp Sufficient Conditions for the Observation, Control, and Stabilization of Waves from the Boundary
• Turnpike Theory
• The periodic turnpike theorem
• Contróle Exact De Léquation De La Chaleur
• Condition nécessaire et suffisante pour la contrôlabilité exacte des ondes
• Rapid Boundary Stabilization of Linear Distributed Systems
• Simultaneous Exact Controllability and Some Applications
• On the Large Time Behavior of Solutions of Hamilton--Jacobi Equations
• Flow Control
• Second Order Optimality Conditions for Semilinear Elliptic Control Problems with Finitely Many State Constraints
• Stable architectures for deep neural networks
• Controllability with Positivity Constraints of the Lotka--McKendrick System
• Steady-State and Periodic Exponential Turnpike Property for Optimal Control Problems in Hilbert Spaces
• Turnpike Properties and Strict Dissipativity for Discrete Time Linear Quadratic Optimal Control Problems
• On the Turnpike Phenomenon for Optimal Boundary Control Problems with Hyperbolic Systems
• Phase portrait control for 1D monostable and bistable reaction–diffusion equations
• Strict Dissipativity Implies Turnpike Behavior for Time-Varying Discrete Time Optimal Control Problems
• Second-Order Necessary and Sufficient Optimality Conditions for Optimization Problems and Applications to Control Theory
• Risk-Sensitive Control on an Infinite Time Horizon
• Minimal controllability time for the heat equation under unilateral state or control constraints
• The Finite-Time Turnpike Phenomenon for Optimal Control Problems: Stabilization by Non-smooth Tracking Terms
• The turnpike property in semilinear control
• Exponential Turnpike property for fractional parabolic equations with non-zero exterior data
• Abstract nonlinear sensitivity and turnpike analysis and an application to semilinear parabolic PDEs
• Structure-preserving deep learning
• Turnpike in Lipschitz—nonlinear optimal control
• Efficient Model Predictive Control for Parabolic PDEs with Goal Oriented Error Estimation
• Deep Neural Networks, Generic Universal Interpolation, and Controlled ODEs
• Initial Data Identification for the One-Dimensional Burgers Equation
• Quantitative Stability for Eigenvalues of Schrödinger Operator, Quantitative Bathtub Principle, and Application to the Turnpike Property for a Bilinear Optimal Control Problem
• Turnpike Properties in Optimal Control: An Overview of Discrete-Time and Continuous-Time Results
• Turnpike properties of optimal relaxed control problems
• Local controllability of reaction-diffusion systems around nonnegative stationary states
• The Inverse Problem for Hamilton--Jacobi Equations and Semiconcave Envelopes
• Optimal shape design for 2D heat equations in large time
• Classical System Theory Revisited for Turnpike in Standard State Space Systems and Impulse Controllable Descriptor Systems
• Large time behavior of unbounded solutions of first-order Hamilton–Jacobi equations in  R N
• Sensitivity Analysis of Optimal Control for a Class of Parabolic PDEs Motivated by Model Predictive Control
• Approximation of high-dimensional parametric PDEs
• Remarks on Long Time Versus Steady State Optimal Control
• A Spillover Phenomenon in the Optimal Location of Actuators
• Propagation, Observation, and Control of Waves Approximated by Finite Difference Methods
• Periodic Optimal Control, Dissipativity and MPC
• Turbulence, Coherent Structures, Dynamical Systems and Symmetry
• Long Time versus Steady State Optimal Control
• Turnpike theorems by a value function approach
• A Note on the Semiglobal Controllability of the Semilinear Wave Equation
• Uniform Asymptotic Stability of Evolutionary Processes in a Banach Space
• Long-Term Values in Markov Decision Processes and Repeated Games, and a New Distance for Probability Spaces
• Null-controllability of perturbed porous medium gas flow
• Neural network approximation
• Dissipative systems analysis and control. Theory and applications
• Optimal control
• Approximation by superpositions of a sigmoidal function
• Mathematical control theory: an introduction
• Exact controllability of semilinear evolution systems and its application
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item

This page was built for publication: Turnpike in optimal control of PDEs, ResNets, and beyond