A machine learning approach to adaptive robust utility maximization and hedging
From MaRDI portal
(Redirected from Publication:5162848)
Abstract: We investigate the adaptive robust control framework for portfolio optimization and loss-based hedging under drift and volatility uncertainty. Adaptive robust problems offer many advantages but require handling a double optimization problem (infimum over market measures, supremum over the control) at each instance. Moreover, the underlying Bellman equations are intrinsically multi-dimensional. We propose a novel machine learning approach that solves for the local saddle-point at a chosen set of inputs and then uses a nonparametric (Gaussian process) regression to obtain a functional representation of the value function. Our algorithm resembles control randomization and regression Monte Carlo techniques but also brings multiple innovations, including adaptive experimental design, separate surrogates for optimal control and the local worst-case measure, and computational speed-ups for the sup-inf optimization. Thanks to the new scheme we are able to consider settings that have been previously computationally intractable and provide several new financial insights about learning and optimal trading under unknown market parameters. In particular, we demonstrate the financial advantages of adaptive robust framework compared to adaptive and static robust alternatives.
Recommendations
Cites work
- A numerical algorithm for fully nonlinear HJB equations: an approach by control randomization
- A probabilistic numerical method for optimal multiple switching problems in high dimension
- A QUANTIZATION TREE METHOD FOR PRICING AND HEDGING MULTIDIMENSIONAL AMERICAN OPTIONS
- Adaptive robust control under model uncertainty
- AN OPTIMAL MARKOVIAN QUANTIZATION ALGORITHM FOR MULTI-DIMENSIONAL STOCHASTIC CONTROL PROBLEMS
- Applying experimental design and regression splines to high-dimensional continuous-state stochastic dynamic programming
- Approximate Dynamic Programming
- Approximate policy iteration: a survey and some new methods
- Deep neural networks algorithms for stochastic control problems on finite horizon: convergence analysis
- Dynamic portfolio optimization with liquidity cost and market impact: a simulation-and-regression approach
- Gaussian processes for machine learning.
- scientific article; zbMATH DE number 1971733 (Why is no real title available?)
- Multi-period mean-variance portfolio optimization based on Monte-Carlo simulation
- Optimal hedging and parameter uncertainty
- Recursive construction of confidence regions
- Regression methods for stochastic control problems and their convergence analysis
- Robust control and model misspecification
- Statistical emulators for pricing and hedging longevity risk products
- Statistical learning for probability-constrained stochastic optimal control
- The design and analysis of computer experiments
Cited in
(5)- Prescriptive selection of machine learning hyperparameters with applications in power markets: retailer's optimal trading
- Learning a functional control for high-frequency finance
- Adaptive robust control in continuous time
- Nonparametric Adaptive Robust Control under Model Uncertainty
- Data-driven nonparametric robust control under dependence uncertainty
This page was built for publication: A machine learning approach to adaptive robust utility maximization and hedging
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5162848)
