A scheme for automatic differentiation of complex loss functions

Abstract

For a real function, automatic differentiation is such a standard algorithm used to efficiently compute its gradient, that it is integrated in various neural network frameworks. However, despite the recent advances in using complex functions in machine learning and the well-established usefulness of automatic differentiation, the support of automatic differentiation for complex functions is not as well-established and widespread as for real functions. In this work we propose an efficient and seamless scheme to implement automatic differentiation for complex functions, which is a compatible generalization of the current scheme for real functions. This scheme can significantly simplify the implementation of neural networks which use complex numbers.

6 pages, 1 figure, 1 table

References in corpus (12)

• The density-matrix renormalization group in the age of matrix product states
• Machine learning and the physical sciences
• Neural-Network Approach to Dissipative Quantum Many-Body Dynamics
• Quantum many-body dynamics in two dimensions with artificial neural networks
• Variational Quantum Monte Carlo Method with a Neural-Network Ansatz for Open Quantum Systems
• Variational neural network ansatz for steady states in open quantum systems
• Differentiable Programming Tensor Networks
• Variational Matrix Product Operators for the Steady State of Dissipative Quantum Systems
• Constructing neural stationary states for open quantum many-body systems
• A Differentiable Programming System to Bridge Machine Learning and Scientific Computing
• Learning the dynamics of open quantum systems from their steady states
• Automatic Differentiation for Second Renormalization of Tensor Networks

Cited by in corpus (11)

• Hybrid Quantum-Classical Convolutional Neural Networks
• Near-Term Quantum Computing Techniques: Variational Quantum Algorithms, Error Mitigation, Circuit Compilation, Benchmarking and Classical Simulation
• Quantifying Non-Markovianity in Open Quantum Dynamics
• Emergence of steady currents due to strong prethermalization
• Reconstructing Non-Markovian Open Quantum Evolution From Multi-time Measurements
• Randomised benchmarking for characterizing and forecasting correlated processes
• Density Matrix Renormalization Group Algorithm For Mixed Quantum States
• Differentiable matrix product states for simulating variational quantum computational chemistry
• Fast Laser Cooling Using Optimal Quantum Control
• Variational approach to open quantum systems with long-range competing interactions
• Fully differentiable optimization protocols for non-equilibrium steady states