Data-driven nonparametric robust control under dependence uncertainty

DOI10.3934/FMF.2023004zbMATH Open1519.91236arXiv2209.04976OpenAlexW4323341994MaRDI QIDQ6105378FDOQ6105378

Authors: Erhan Bayraktar, Tao Chen 

Publication date: 26 June 2023

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

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.

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

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

zbMATH Keywords

copulamachine learningWasserstein distancemodel uncertaintystochastic controlutility maximizationadaptive robust dynamic programmingMarkovian control problemnonparametric adaptive robust controlstochastic gradient descent ascent

Mathematics Subject Classification ID

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

Cites Work

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

Cited In (4)

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

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)