Data-driven nonparametric robust control under dependence uncertainty

DOI10.3934/FMF.2023004MaRDI QIDQ6105378zbMATH OpenOpenAlexFDO

Authors Erhan Bayraktar, Tao Chen

Publication date 26 June 2023

Published in Frontiers of Mathematical Finance (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2209.04976

zbMATH Keywords

adaptive robust dynamic programmingcopulamachine learningMarkovian control problemmodel uncertaintynonparametric adaptive robust controlstochastic controlstochastic gradient descent ascentutility maximizationWasserstein distance

Mathematics Subject Classification ID

Dynamic programming (90C39) Financial markets (91G15) Numerical methods (including Monte Carlo methods) (91G60) Optimal stochastic control (93E20) Stochastic learning and adaptive control (93E35)

Abstract: We consider a multi-period stochastic control problem where the multivariate driving stochastic factor of the system has known marginal distributions but uncertain dependence structure. To solve the problem, we propose to implement the nonparametric adaptive robust control framework. We aim to find the optimal control against the worst-case copulae in a sequence of shrinking uncertainty sets which are generated from continuously observing the data. Then, we use a stochastic gradient descent ascent algorithm to numerically handle the corresponding high dimensional dynamic inf-sup optimization problem. We present the numerical results in the context of utility maximization and show that the controller benefits from knowing more information about the uncertain model.

Recommendations

• Nonparametric Adaptive Robust Control under Model Uncertainty
• Adaptive robust control under model uncertainty
• Stochastic and adaptive optimal control of uncertain interconnected systems: a data-driven approach
• Adaptive robust control in continuous time
• A control problem with dominating uncertainty

Cites work

• A machine learning approach to adaptive robust utility maximization and hedging
• Bayesian dynamic programming
• Central limit theorems for the Wasserstein distance between the empirical and the true distributions
• Data-driven distributionally robust optimization using the Wasserstein metric: performance guarantees and tractable reformulations
• Gaussian processes for machine learning.
• Identification and stochastic adaptive control
• Maxmin expected utility with non-unique prior
• On the rate of convergence in Wasserstein distance of the empirical measure
• Online drift estimation for jump-diffusion processes
• Recursive construction of confidence regions
• Stochastic optimal control. The discrete time case
• Stochastic Systems
• Time-inconsistent Markovian control problems under model uncertainty with application to the mean-variance portfolio selection

Cited in

(4)

• Data-based robust optimal control of continuous-time affine nonlinear systems with matched uncertainties
• Wasserstein Distributionally Robust Stochastic Control: A Data-Driven Approach
• Nonparametric Adaptive Robust Control under Model Uncertainty
• Distributionally robust chance-constrained Markov decision processes with random payoff

This page was built for publication: Data-driven nonparametric robust control under dependence uncertainty

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6105378)