Deep Learning for Constrained Utility Maximisation

被引:2
|
作者
Davey, Ashley [1 ]
Zheng, Harry [1 ]
机构
[1] Imperial Coll, Dept Math, London SW7 2BZ, England
基金
英国工程与自然科学研究理事会;
关键词
Stochastic control; Deep learning; Primal and dual BSDEs; HJB equation; Utility maximisation; PARTIAL-DIFFERENTIAL-EQUATIONS; STOCHASTIC-CONTROL; ALGORITHMS; NETWORKS;
D O I
10.1007/s11009-021-09912-3
中图分类号
O21 [概率论与数理统计]; C8 [统计学];
学科分类号
020208 ; 070103 ; 0714 ;
摘要
This paper proposes two algorithms for solving stochastic control problems with deep learning, with a focus on the utility maximisation problem. The first algorithm solves Markovian problems via the Hamilton Jacobi Bellman (HJB) equation. We solve this highly nonlinear partial differential equation (PDE) with a second order backward stochastic differential equation (2BSDE) formulation. The convex structure of the problem allows us to describe a dual problem that can either verify the original primal approach or bypass some of the complexity. The second algorithm utilises the full power of the duality method to solve non-Markovian problems, which are often beyond the scope of stochastic control solvers in the existing literature. We solve an adjoint BSDE that satisfies the dual optimality conditions. We apply these algorithms to problems with power, log and non-HARA utilities in the Black-Scholes, the Heston stochastic volatility, and path dependent volatility models. Numerical experiments show highly accurate results with low computational cost, supporting our proposed algorithms.
引用
收藏
页码:661 / 692
页数:32
相关论文
共 50 条
  • [31] Utility Maximisation with Fairness Constraints: Perspectives of an Ethically Justifiable Cost-Utility Analysis
    Marckmann, G.
    [J]. GESUNDHEITSWESEN, 2009, 71 : S2 - S8
  • [32] Utility maximisation in a factor model with constant and proportional transaction costs
    Belak, Christoph
    Christensen, Soeren
    [J]. FINANCE AND STOCHASTICS, 2019, 23 (01) : 29 - 96
  • [33] Sensitivity analysis of the utility maximisation problem with respect to model perturbations
    Mostovyi, Oleksii
    Sirbu, Mihai
    [J]. FINANCE AND STOCHASTICS, 2019, 23 (03) : 595 - 640
  • [34] Sensitivity analysis of the utility maximisation problem with respect to model perturbations
    Oleksii Mostovyi
    Mihai Sîrbu
    [J]. Finance and Stochastics, 2019, 23 : 595 - 640
  • [35] Geometry Aware Constrained Optimization Techniques for Deep Learning
    Roy, Soumava Kumar
    Mhammedi, Zakaria
    Harandi, Mehrtash
    [J]. 2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018, : 4460 - 4469
  • [36] Deep Learning of Constrained Autoencoders for Enhanced Understanding of Data
    Ayinde, Babajide O.
    Zurada, Jacek M.
    [J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2018, 29 (09) : 3969 - 3979
  • [37] Physics-Constrained Deep Learning of Geomechanical Logs
    Chen, Yuntian
    Zhang, Dongxiao
    [J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2020, 58 (08): : 5932 - 5943
  • [38] Constrained attractor selection using deep reinforcement learning
    Wang, Xue-She
    Turner, James D.
    Mann, Brian P.
    [J]. JOURNAL OF VIBRATION AND CONTROL, 2021, 27 (5-6) : 502 - 514
  • [39] Constrained deep reinforcement learning for maritime platform defense
    Markowitz, Jared
    [J]. ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING FOR MULTI-DOMAIN OPERATIONS APPLICATIONS VI, 2024, 13051
  • [40] Constrained Deep Transfer Feature Learning and its Applications
    Wu, Yue
    Ji, Qiang
    [J]. 2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, : 5101 - 5109