Quantum Deep Hedging

Abstract

Quantum machine learning has the potential for a transformative impact across industry sectors and in particular in finance. In our work we look at the problem of hedging where deep reinforcement learning offers a powerful framework for real markets. We develop quantum reinforcement learning methods based on policy-search and distributional actor-critic algorithms that use quantum neural network architectures with orthogonal and compound layers for the policy and value functions. We prove that the quantum neural networks we use are trainable, and we perform extensive simulations that show that quantum models can reduce the number of trainable parameters while achieving comparable performance and that the distributional approach obtains better performance than other standard approaches, both classical and quantum. We successfully implement the proposed models on a trapped-ion quantum processor, utilizing circuits with up to $16$ qubits, and observe performance that agrees well with noiseless simulation. Our quantum techniques are general and can be applied to other reinforcement learning problems beyond hedging.

References in corpus (40)

• A Brief Survey of Deep Reinforcement Learning
• Variational Quantum Algorithms
• Supervised learning with quantum enhanced feature spaces
• Barren plateaus in quantum neural network training landscapes
• Quantum Circuit Learning
• Evaluating analytic gradients on quantum hardware
• The effect of data encoding on the expressive power of variational quantum machine learning models
• Integration with respect to the Haar measure on unitary, orthogonal and symplectic group
• Data re-uploading for a universal quantum classifier
• A rigorous and robust quantum speed-up in supervised machine learning
• A generative modeling approach for benchmarking and training shallow quantum circuits
• Quantum computational finance: Monte Carlo pricing of financial derivatives
• Diagnosing Barren Plateaus with Tools from Quantum Optimal Control
• Theory of overparametrization in quantum neural networks
• Group-Invariant Quantum Machine Learning
• Optimizing quantum optimization algorithms via faster quantum gradient computation
• A Survey of Quantum Computing for Finance
• Quantum Methods for Neural Networks and Application to Medical Image Classification
• The power of block-encoded matrix powers: improved regression techniques via faster Hamiltonian simulation
• Constrained Quantum Optimization for Extractive Summarization on a Trapped-ion Quantum Computer
• Efficient classical simulation of matchgate circuits with generalized inputs and measurements
• Variational inference with a quantum computer
• Fermion Sampling: a robust quantum computational advantage scheme using fermionic linear optics and magic input states
• Grassmannian Learning: Embedding Geometry Awareness in Shallow and Deep Learning
• Pseudo-dimension of quantum circuits
• A Survey on Quantum Reinforcement Learning
• Quantum Machine Learning in Finance: Time Series Forecasting
• Quantum Reinforcement Learning via Policy Iteration
• Escaping from the Barren Plateau via Gaussian Initializations in Deep Variational Quantum Circuits
• Quantum Computing Methods for Supply Chain Management
• A Convergence Theory for Over-parameterized Variational Quantum Eigensolvers
• Classical and Quantum Algorithms for Orthogonal Neural Networks
• Playing Atari with Hybrid Quantum-Classical Reinforcement Learning
• Unentangled quantum reinforcement learning agents in the OpenAI Gym
• Quantum Algorithms for Reinforcement Learning with a Generative Model
• Quantum algorithm for stochastic optimal stopping problems with applications in finance
• Expressivity of Variational Quantum Machine Learning on the Boolean Cube
• Financial Risk Management on a Neutral Atom Quantum Processor
• Quantum machine learning with subspace states
• Quantum policy gradient algorithms

Cited by in corpus (10)

• Quantum computing for finance
• Barren Plateaus in Variational Quantum Computing
• Does provable absence of barren plateaus imply classical simulability?
• The Adjoint Is All You Need: Characterizing Barren Plateaus in Quantum Ansätze
• Hybrid quantum physics-informed neural networks for simulating computational fluid dynamics in complex shapes
• Quantum Convolutional Neural Networks are Effectively Classically Simulable
• Quantum encoder for fixed Hamming-weight subspaces
• Pitfalls when tackling the exponential concentration of parameterized quantum models
• Architectures and random properties of symplectic quantum circuits
• Trainability issues in quantum policy gradients