Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
143 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
46 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Fast Deep Hedging with Second-Order Optimization (2410.22568v1)

Published 29 Oct 2024 in q-fin.RM, cs.LG, and q-fin.CP

Abstract: 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.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (41)
  1. Shun-ichi Amari. 1998. Natural Gradient Works Efficiently in Learning. Neural Computation 10, 2 (1998), 251–276.
  2. What Matters In On-Policy Reinforcement Learning? A Large-Scale Empirical Study. arXiv:2006.05990
  3. Distributed Second-Order Optimization Using Kronecker-Factored Approximations. In International Conference on Learning Representations.
  4. Mark Broadie and Özgür Kaya. 2006. Exact Simulation of Stochastic Volatility and Other Affine Jump Diffusion Processes. Operations Research 54, 2 (2006), 217–231.
  5. Hans Buehler. 2017. Statistical Hedging. SSNR: 2913250.
  6. Deep Hedging. Quantitative Finance 19, 8 (2019), 1271–1291.
  7. Alexandre Carbonneau. 2021. Deep Hedging of Long-Term Financial Derivatives. Insurance: Mathematics and Economics 99 (2021), 327–340.
  8. Adaptive Gradient Methods at the Edge of Stability. arXiv:2207.14484
  9. Natural Neural Networks. In Advances in Neural Information Processing Systems, Vol. 28. Curran Associates, Inc., 2071–2079.
  10. Jeffrey Elman. 1990. Finding Structure in Time. Cognitive Science 14, 2 (1990), 179–211.
  11. Fast Approximate Natural Gradient Descent in a Kronecker Factored Eigenbasis. In Advances in Neural Information Processing Systems, Vol. 31. Curran Associates, Inc., 9573–9583.
  12. Roger Grosse. 2022. Lecture Notes on Neural Net Training Dynamics (Chapter 3: Metrics). https://www.cs.toronto.edu/~rgrosse/courses/csc2541_2022/readings/L03_metrics.pdf
  13. Mastering Diverse Domains through World Models. arXiv:2301.04104
  14. Recent Advances in Reinforcement Learning in Finance. Mathematical Finance 33, 3 (2023), 437–503.
  15. Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification. In International Conference on Computer Vision. IEEE, 1026–1034.
  16. Steven Heston. 1993. A Closed-Form Solution for Options with Stochastic Volatility with Applications to Bond and Currency Options. The review of financial studies 6, 2 (1993), 327–343.
  17. Sepp Hochreiter and Jürgen Schmidhuber. 1997. Long Short-Term Memory. Neural Computation 9, 8 (1997), 1735–1780.
  18. Deep Hedging under Rough Volatility. Risks 9, 7 (2021), 138.
  19. Herbert Jaeger. 2002. Tutorial on training recurrent neural networks, covering BPPT, RTRL, EKF and the” echo state network” approach. Vol. 5. GMD-Forschungszentrum Informationstechnik Bonn.
  20. Sham M Kakade. 2001. A Natural Policy Gradient. In Advances in Neural Information Processing Systems, Vol. 14. MIT Press, 1531–1538.
  21. Diederik Kingma and Jimmy Ba. 2015. Adam: A Method for Stochastic Optimization. In International Conference on Learning Representations.
  22. The Geometry of Neural Nets’ Parameter Spaces Under Reparametrization. In Advances in Neural Information Processing Systems, Vol. 36. Curran Associates, Inc., 17669–17688.
  23. Olivier Ledoit and Michael Wolf. 2004. A Well-Conditioned Estimator for Large-Dimensional Covariance Matrices. Journal of Multivariate Analysis 88, 2 (2004), 365–411.
  24. Olivier Ledoit and Michael Wolf. 2021. Shrinkage Estimation of Large Covariance Matrices: Keep It Simple, Statistician? Journal of Multivariate Analysis 186 (2021), 104796.
  25. Robust Deep Hedging. Quantitative Finance 22, 8 (2022), 1465–1480.
  26. James Martens. 2020. New Insights and Perspectives on the Natural Gradient Method. Journal of Machine Learning Research 21, 146 (2020), 1–76.
  27. Kronecker-Factored Curvature Approximations for Recurrent Neural Networks. In International Conference on Learning Representations.
  28. James Martens and Roger Grosse. 2015. Optimizing Neural Networks with Kronecker-factored Approximate Curvature. In International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 37). PMLR, 2408–2417.
  29. James Martens and Ilya Sutskever. 2011. Learning Recurrent Neural Networks with Hessian-Free Optimization. In International Conference on Machine Learning. 1033–1040.
  30. James Martens and Ilya Sutskever. 2012. Training Deep and Recurrent Networks with Hessian-Free Optimization. In Neural Networks: Tricks of the Trade. Vol. 7700. Springer, 479–535.
  31. Monte Carlo Gradient Estimation in Machine Learning. Journal of Machine Learning Research 21, 132 (2020), 1–62.
  32. Deep Hedging: Continuous Reinforcement Learning for Hedging of General Portfolios across Multiple Risk Aversions. In ACM International Conference on AI in Finance. ACM, 361–368.
  33. Resurrecting Recurrent Neural Networks for Long Sequences. In International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 202). PMLR, 26670–26698.
  34. Johannes Ruf and Weiguan Wang. 2020. Neural Networks for Option Pricing and Hedging: A Literature Review. Journal of Computational Finance (2020).
  35. Nicol Schraudolph. 2002. Fast Curvature Matrix-Vector Products for Second-Order Gradient Descent. Neural Computation 14, 7 (2002), 1723–1738.
  36. Trust Region Policy Optimization. In International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 37). PMLR, 1889–1897.
  37. Martin Schweizer. 1995. Variance-Optimal Hedging in Discrete Time. Mathematics of Operations Research 20, 1 (1995), 1–32.
  38. Artur Sepp and Parviz Rakhmonov. 2024. Log-Normal Stochastic Volatility Model with Quadratic Drift. SSNR: 2522425.
  39. Rich Information Is Affordable: A Systematic Performance Analysis of Second-order Optimization Using K-FAC. In ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. ACM, 2145–2153.
  40. Scalable Trust-Region Method for Deep Reinforcement Learning Using Kronecker-factored Approximation. In Advances in Neural Information Processing Systems, Vol. 30. Curran Associates, Inc., 5285–5294.
  41. Biao Zhang and Rico Sennrich. 2019. Root Mean Square Layer Normalization. In Advances in Neural Information Processing Systems, Vol. 32. Curran Associates, Inc., 12360–12371.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets