Efficient trainability of linear optical modules in quantum optical neural networks

Abstract

The existence of "barren plateau landscapes" for generic discrete variable quantum neural networks, which obstructs efficient gradient-based optimization of cost functions defined by global measurements, would be surprising in the case of generic linear optical modules in quantum optical neural networks due to the tunability of the intensity of continuous variable states and the relevant unitary group having exponentially smaller dimension. We demonstrate that coherent light in $m$ modes can be generically compiled efficiently if the total intensity scales sublinearly with $m$, and extend this result to cost functions based on homodyne, heterodyne, or photon detection measurement statistics, and to noisy cost functions in the presence of attenuation. We further demonstrate efficient trainability of $m$ mode linear optical quantum circuits for variational mean field energy estimation of positive quadratic Hamiltonians for input states that do not have energy exponentially vanishing with $m$.

arXiv comment8 pages

References in corpus (18)

• A variational eigenvalue solver on a quantum processor
• Gaussian Quantum Information
• Deep Learning with Coherent Nanophotonic Circuits
• Barren plateaus in quantum neural network training landscapes
• The theory of variational hybrid quantum-classical algorithms
• Noise-Induced Barren Plateaus in Variational Quantum Algorithms
• Efficient Learning for Deep Quantum Neural Networks
• Exact and Approximate Unitary 2-Designs: Constructions and Applications
• Efficient Classical Simulation of Continuous Variable Quantum Information Processes
• Quantum-assisted quantum compiling
• Exactly-Solvable Models Derived from a Generalized Gaudin Algebra
• A detailed study of Gaussian Boson Sampling
• Large gradients via correlation in random parameterized quantum circuits
• Variational Quantum Unsampling on a Quantum Photonic Processor
• Local asymptotic normality for qubit states
• Bosonic quadratic Hamiltonians
• Optimal and near-optimal probe states for quantum metrology of number conserving two-mode bosonic Hamiltonians
• Generating accessible entanglement in bosons via pair-correlated tunneling

Cited by in corpus (1)

• Large gradients via correlation in random parameterized quantum circuits