Deep Learning for Constrained Utility Maximisation

被引:0
|
作者
Ashley Davey
Harry Zheng
机构
[1] Imperial College,Department of Mathematics
关键词
Stochastic control; Deep learning; Primal and dual BSDEs; HJB equation; Utility maximisation; 93E20; 91G80; 90C46; 49M29;
D O I
暂无
中图分类号
学科分类号
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:31
相关论文
共 50 条
  • [41] Hard-Constrained Deep Learning for Climate Downscaling
    Harder, Paula
    Hernandez-Garcia, Alex
    Ramesh, Venkatesh
    Yang, Qidong
    Sattegeri, Prasanna
    Szwarcman, Daniela
    Watson, Campbell D.
    Rolnick, David
    [J]. JOURNAL OF MACHINE LEARNING RESEARCH, 2023, 24
  • [42] Deep Learning for Hardware-Constrained Driverless Cars
    Sreedhar, Bharathwaj Krishnaswami
    Shunmugam, Nagarajan
    [J]. 2020 IEEE 44TH ANNUAL COMPUTERS, SOFTWARE, AND APPLICATIONS CONFERENCE (COMPSAC 2020), 2020, : 26 - 29
  • [43] Explaining Deep Learning Models with Constrained Adversarial Examples
    Moore, Jonathan
    Hammerla, Nils
    Watkins, Chris
    [J]. PRICAI 2019: TRENDS IN ARTIFICIAL INTELLIGENCE, PT I, 2019, 11670 : 43 - 56
  • [44] Training Deep Neural Networks with Constrained Learning Parameters
    Date, Prasanna
    Carothers, Christopher D.
    Mitchell, John E.
    Hendler, James A.
    Magdon-Ismail, Malik
    [J]. 2020 INTERNATIONAL CONFERENCE ON REBOOTING COMPUTING (ICRC 2020), 2020, : 107 - 115
  • [45] Utility maximisation for resource allocation of migrating enterprise applications into the cloud
    Li, Shiyong
    Sun, Wei
    [J]. ENTERPRISE INFORMATION SYSTEMS, 2021, 15 (02) : 197 - 229
  • [46] Extended weak convergence and utility maximisation with proportional transaction costs
    Erhan Bayraktar
    Leonid Dolinskyi
    Yan Dolinsky
    [J]. Finance and Stochastics, 2020, 24 : 1013 - 1034
  • [47] Utility maximisation in a factor model with constant and proportional transaction costs
    Christoph Belak
    Sören Christensen
    [J]. Finance and Stochastics, 2019, 23 : 29 - 96
  • [48] Extended weak convergence and utility maximisation with proportional transaction costs
    Bayraktar, Erhan
    Dolinskyi, Leonid
    Dolinsky, Yan
    [J]. FINANCE AND STOCHASTICS, 2020, 24 (04) : 1013 - 1034
  • [49] Utility maximisation and utility indifference price for exponential semi-martingale models and HARA utilities
    Ellanskaya, A.
    Vostrikova, L.
    [J]. PROCEEDINGS OF THE STEKLOV INSTITUTE OF MATHEMATICS, 2014, 287 (01) : 68 - 95
  • [50] The Utility of Deep Learning in Breast Ultrasonic Imaging: A Review
    Fujioka, Tomoyuki
    Mori, Mio
    Kubota, Kazunori
    Oyama, Jun
    Yamaga, Emi
    Yashima, Yuka
    Katsuta, Leona
    Nomura, Kyoko
    Nara, Miyako
    Oda, Goshi
    Nakagawa, Tsuyoshi
    Kitazume, Yoshio
    Tateishi, Ukihide
    [J]. DIAGNOSTICS, 2020, 10 (12)