Fast Deep Hedging with Second-Order Optimization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Mueller, Konrad, Akkari, Amira, Gonon, Lukas, Wood, Ben
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912095442829312
author Mueller, Konrad
Akkari, Amira
Gonon, Lukas
Wood, Ben
author_facet Mueller, Konrad
Akkari, Amira
Gonon, Lukas
Wood, Ben
contents Hedging exotic options in presence of market frictions is an important risk management task. Deep hedging can solve such hedging problems by training neural network policies in realistic simulated markets. Training these neural networks may be delicate and suffer from slow convergence, particularly for options with long maturities and complex sensitivities to market parameters. To address this, we propose a second-order optimization scheme for deep hedging. We leverage pathwise differentiability to construct a curvature matrix, which we approximate as block-diagonal and Kronecker-factored to efficiently precondition gradients. We evaluate our method on a challenging and practically important problem: hedging a cliquet option on a stock with stochastic volatility by trading in the spot and vanilla options. We find that our second-order scheme can optimize the policy in 1/4 of the number of steps that standard adaptive moment-based optimization takes.
format Preprint
id arxiv_https___arxiv_org_abs_2410_22568
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Fast Deep Hedging with Second-Order Optimization
Mueller, Konrad
Akkari, Amira
Gonon, Lukas
Wood, Ben
Risk Management
Machine Learning
Computational Finance
Hedging exotic options in presence of market frictions is an important risk management task. Deep hedging can solve such hedging problems by training neural network policies in realistic simulated markets. Training these neural networks may be delicate and suffer from slow convergence, particularly for options with long maturities and complex sensitivities to market parameters. To address this, we propose a second-order optimization scheme for deep hedging. We leverage pathwise differentiability to construct a curvature matrix, which we approximate as block-diagonal and Kronecker-factored to efficiently precondition gradients. We evaluate our method on a challenging and practically important problem: hedging a cliquet option on a stock with stochastic volatility by trading in the spot and vanilla options. We find that our second-order scheme can optimize the policy in 1/4 of the number of steps that standard adaptive moment-based optimization takes.
title Fast Deep Hedging with Second-Order Optimization
topic Risk Management
Machine Learning
Computational Finance
url https://arxiv.org/abs/2410.22568