Quantum Optimization for Training Quantum Neural Networks
arXiv:2103.17047 · doi:10.1007/s42484-024-00169-w
Abstract
Training quantum neural networks (QNNs) using gradient-based or gradient-free classical optimisation approaches is severely impacted by the presence of barren plateaus in the cost landscapes. In this paper, we devise a framework for leveraging quantum optimisation algorithms to find optimal parameters of QNNs for certain tasks. To achieve this, we coherently encode the cost function of QNNs onto relative phases of a superposition state in the Hilbert space of the network parameters. The parameters are tuned with an iterative quantum optimisation structure using adaptively selected Hamiltonians. The quantum mechanism of this framework exploits hidden structure in the QNN optimisation problem and hence is expected to provide beyond-Grover speed up, mitigating the barren plateau issue.
arXiv comment35 pages, 30 figures, 1 animation
References in corpus (36)
- A variational eigenvalue solver on a quantum processor
- Gaussian Quantum Information
- Barren plateaus in quantum neural network training landscapes
- The theory of variational hybrid quantum-classical algorithms
- Quantum Circuit Learning
- Quantum fingerprinting
- Cost Function Dependent Barren Plateaus in Shallow Parametrized Quantum Circuits
- Shortcuts to adiabaticity: concepts, methods, and applications
- Circuit-centric quantum classifiers
- Noise-Induced Barren Plateaus in Variational Quantum Algorithms
- Simulating Hamiltonian dynamics with a truncated Taylor series
- From the Quantum Approximate Optimization Algorithm to a Quantum Alternating Operator Ansatz
- Quantum singular value transformation and beyond: exponential improvements for quantum matrix arithmetics
- Efficient Classical Simulation of Continuous Variable Quantum Information Processes
- A generative modeling approach for benchmarking and training shallow quantum circuits
- Layerwise learning for quantum neural networks
- Obstacles to State Preparation and Variational Optimization from Symmetry Protection
- Experimental Quantum Generative Adversarial Networks for Image Generation
- Effect of barren plateaus on gradient-free optimization
- Improving Variational Quantum Optimization using CVaR
- Optimal Quantum Measurements of Expectation Values of Observables
- Grover Adaptive Search for Constrained Polynomial Binary Optimization
- Near-optimal quantum circuit for Grover's unstructured search using a transverse field
- Quantum stochastic walks: A generalization of classical random walks and quantum walks
- Shortcuts to Adiabaticity in Digitized Adiabatic Quantum Computing
- Optimizing quantum optimization algorithms via faster quantum gradient computation
- Learning and Inference on Generative Adversarial Quantum Circuits
- Learning to Optimize Variational Quantum Circuits to Solve Combinatorial Problems
- On the Universality of the Quantum Approximate Optimization Algorithm
- Reinforcement Learning for Many-Body Ground-State Preparation Inspired by Counterdiabatic Driving
- Reinforcement Learning assisted Quantum Optimization
- Generative model benchmarks for superconducting qubits
- A quantum walk assisted approximate algorithm for bounded NP optimisation problems
- Abrupt Transitions in Variational Quantum Circuit Training
- Quantum search with hybrid adiabatic-quantum walk algorithms and realistic noise
- Low depth mechanisms for quantum optimization