Singular perturbations in stochastic optimal control with unbounded data

DOI10.1051/COCV/2023020MaRDI QIDQ6138481zbMATH OpenOpenAlexFDO

Authors Martino Bardi, Hicham Kouhkouh

Publication date 5 September 2023

Published in ESAIM: Control, Optimisation and Calculus of Variations (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://arxiv.org/abs/2208.00655

zbMATH Keywords

Hamilton-Jacobi-Bellman equationshomogenizationinvariant measuressingular perturbationsstochastic optimal controlviscosity solutionstwo-scale systems

Mathematics Subject Classification ID

Neural networks for/in biological studies, artificial life and related topics (92B20) Viscosity solutions to PDEs (35D40) Hamilton-Jacobi equations (35F21) Methods involving semicontinuity and convergence; relaxation (49J45) Existence of optimal solutions to problems involving randomness (49J55) Viscosity solutions to Hamilton-Jacobi equations in optimal control and differential games (49L25) Time-scale analysis and singular perturbations in control/observation systems (93C70) Optimal stochastic control (93E20)

Abstract: We study singular perturbations of a class of two-scale stochastic control systems with unbounded data. The assumptions are designed to cover some relaxation problems for deep neural networks. We construct effective Hamiltonian and initial data and prove the convergence of the value function to the solution of a limit (effective) Cauchy problem for a parabolic equation of HJB type. We use methods of probability, viscosity solutions and homogenization.

Recommendations

• Deep relaxation of controlled stochastic gradient descent via singular perturbations
• Singular perturbations and optimal control of stochastic systems in infinite dimension: HJB equations and viscosity solutions
• Singular Perturbations in Stochastic Ergodic Control Problems
• scientific article; zbMATH DE number 4132079
• Ergodicity, stabilization, and singular perturbations for Bellman-Isaacs equations

Cites work

• scientific article; zbMATH DE number 3664138 (Why is no real title available?)
• scientific article; zbMATH DE number 2150787 (Why is no real title available?)
• scientific article; zbMATH DE number 1376974 (Why is no real title available?)
• Averaging of singularly perturbed controlled stochastic differential equations
• Averaging principle and normal deviations for multiscale stochastic systems
• Averaging principle for slow-fast stochastic differential equations with time dependent locally Lipschitz coefficients
• Convergence by viscosity methods in multiscale financial models with stochastic volatility
• Deep relaxation: partial differential equations for optimizing deep neural networks
• Entropy-SGD: biasing gradient descent into wide valleys
• Large deviations and importance sampling for systems of slow-fast motion
• Liouville properties and critical value of fully nonlinear elliptic operators
• Measurable relations
• Multiscale stochastic volatility for equity, interest rate, and credit derivatives.
• On Poisson equation and diffusion approximation. II.
• On polynomial mixing bounds for stochastic differential equations
• On the Poisson equation and diffusion approximation. I
• On the Poisson equation and diffusion approximation. III
• Optimal control and viscosity solutions of Hamilton-Jacobi-Bellman equations
• Optimal control with random parameters: a multiscale approach
• Rate of convergence for singular perturbations of Hamilton-Jacobi equations in unbounded spaces
• Simultaneous small noise limit for singularly perturbed slow-fast coupled diffusions
• Singular Perturbations in Ergodic Control of Diffusions
• Singular limit of BSDEs and optimal control of two scale stochastic systems in infinite dimensional spaces
• Singular perturbations and optimal control of stochastic systems in infinite dimension: HJB equations and viscosity solutions
• Singular perturbations of nonlinear degenerate parabolic pDEs: A general convergence result
• Small-time asymptotics for fast mean-reverting stochastic volatility models
• Stochastic differential equations and applications.
• The Kantorovich and variation distances between invariant measures of diffusions and nonlinear stationary Fokker-Planck-Kolmogorov equations
• The averaging principle for non-autonomous slow-fast stochastic differential equations and an application to a local stochastic volatility model
• The ergodic problem for some subelliptic operators with unbounded coefficients
• The perturbed test function method for viscosity solutions of nonlinear PDE
• Transition times and stochastic resonance for multidimensional diffusions with time periodic drift: a large deviations approach
• Uniqueness Results for Second-Order Bellman--Isaacs Equations under Quadratic Growth Assumptions and Applications
• Viscosity Solutions Methods for Singular Perturbations in Deterministic and Stochastic Control
• Viscosity methods for large deviations estimates of multiscale stochastic processes
• Weak convergence methods and singularly perturbed stochastic control and filtering problems

Cited in

(4)

• A Viscous Ergodic Problem with Unbounded and Measurable Ingredients, Part 1: HJB Equation
• Deep relaxation of controlled stochastic gradient descent via singular perturbations
• A singular stochastic control problem in an unbounded domain
• Stationary equilibria and their stability in a Kuramoto MFG with strong interaction

This page was built for publication: Singular perturbations in stochastic optimal control with unbounded data

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6138481)