11 papers
Deep Learning for Dynamic Programming with Recursive Utility Using First-order Conditions
Xianhua Peng, Wu Guo, Songyan Wang +1
This paper proposes the certainty-equivalent first-order learning (CEFOL) algorithm, a deep learning algorithm for solving discrete-time dynamic programming problems with recursive…
Deep Learning for Dynamic Programming with Recursive Utility
Xianhua Peng, Wu Guo
We propose the first deep learning algorithm, the Certainty Equivalent Learning (CEL) algorithm, for solving high-dimensional discrete-time dynamic programming problems with recurs…
A Machine Learning Algorithm for Finite-Horizon Stochastic Control Problems in Economics
Xianhua Peng, Steven Kou, Lekang Zhang
We propose a machine learning algorithm for solving finite-horizon stochastic control problems based on a deep neural network representation of the optimal policy functions. The al…
A Risk Sensitive Contract-unified Reinforcement Learning Approach for Option Hedging
Xianhua Peng, Xiang Zhou, Bo Xiao +1
We propose a new risk sensitive reinforcement learning approach for the dynamic hedging of options. The approach focuses on the minimization of the tail risk of the final P&L of th…
Joint Pricing in SPX and VIX Derivative Markets with Composite Change of Time Models
Liexin Cheng, Xue Cheng, Xianhua Peng
The Chicago Board Options Exchange Volatility Index (VIX) is calculated from SPX options and derivatives of VIX are also traded in market, which leads to the so-called ``consistent…
Reinforcement Learning for Financial Index Tracking
Xianhua Peng, Chenyin Gong, Xue Dong He
We propose the first discrete-time infinite-horizon dynamic formulation of the financial index tracking problem under both return-based tracking error and value-based tracking erro…
Surplus-Invariant, Law-Invariant, and Conic Acceptance Sets Must be the Sets Induced by Value-at-Risk
Xue Dong He, Xianhua Peng
The regulator is interested in proposing a capital adequacy test by specifying an acceptance set for firms' capital positions at the end of a given period. This set needs to be sur…
EM Algorithm and Stochastic Control in Economics
Steven Kou, Xianhua Peng, Xingbo Xu
Generalising the idea of the classical EM algorithm that is widely used for computing maximum likelihood estimates, we propose an EM-Control (EM-C) algorithm for solving multi-peri…
On the Measurement of Economic Tail Risk
Steven Kou, Xianhua Peng
This paper attempts to provide a decision-theoretic foundation for the measurement of economic tail risk, which is not only closely related to utility theory but also relevant to s…
Asset Allocation under the Basel Accord Risk Measures
Zaiwen Wen, Xianhua Peng, Xin Liu +2
Financial institutions are currently required to meet more stringent capital requirements than they were before the recent financial crisis; in particular, the capital requirement…
On the Wiener-Hopf factorization for Levy processes with bounded positive jumps
Alexey Kuznetsov, Xianhua Peng
We study the Wiener-Hopf factorization for Levy processes with bounded positive jumps and arbitrary negative jumps. Using the results from the theory of entire functions of Cartwri…