Layerwise learning for quantum neural networks

Abstract

With the increased focus on quantum circuit learning for near-term applications on quantum devices, in conjunction with unique challenges presented by cost function landscapes of parametrized quantum circuits, strategies for effective training are becoming increasingly important. In order to ameliorate some of these challenges, we investigate a layerwise learning strategy for parametrized quantum circuits. The circuit depth is incrementally grown during optimization, and only subsets of parameters are updated in each training step. We show that when considering sampling noise, this strategy can help avoid the problem of barren plateaus of the error surface due to the low depth of circuits, low number of parameters trained in one step, and larger magnitude of gradients compared to training the full circuit. These properties make our algorithm preferable for execution on noisy intermediate-scale quantum devices. We demonstrate our approach on an image-classification task on handwritten digits, and show that layerwise learning attains an 8% lower generalization error on average in comparison to standard learning schemes for training quantum circuits of the same size. Additionally, the percentage of runs that reach lower test errors is up to 40% larger compared to training the full circuit, which is susceptible to creeping onto a plateau during training.

11 pages, 7 figures

References in corpus (44)

• Adam: A Method for Stochastic Optimization
• Supplementary information for "Quantum supremacy using a programmable superconducting processor"
• A variational eigenvalue solver on a quantum processor
• Hardware-efficient Variational Quantum Eigensolver for Small Molecules and Quantum Magnets
• Supervised learning with quantum enhanced feature spaces
• Barren plateaus in quantum neural network training landscapes
• The theory of variational hybrid quantum-classical algorithms
• A Quantum Approximate Optimization Algorithm
• Quantum Circuit Learning
• Quantum Convolutional Neural Networks
• Characterizing Quantum Supremacy in Near-Term Devices
• Evaluating analytic gradients on quantum hardware
• An adaptive variational algorithm for exact molecular simulations on a quantum computer
• Scalable Quantum Simulation of Molecular Energies
• From the Quantum Approximate Optimization Algorithm to a Quantum Alternating Operator Ansatz
• Towards Practical Quantum Variational Algorithms
• Hybrid Quantum-Classical Hierarchy for Mitigation of Decoherence and Determination of Excited States
• Quantum autoencoders for efficient compression of quantum data
• Robust determination of molecular spectra on a quantum processor
• Quantum chemistry calculations on a trapped-ion quantum simulator
• An initialization strategy for addressing barren plateaus in parametrized quantum circuits
• A generative modeling approach for benchmarking and training shallow quantum circuits
• Quantum Approximate Optimization Algorithm for MaxCut: A Fermionic View
• Random Quantum Circuits are Approximate 2-designs
• Hierarchical quantum classifiers
• Quantum Implementation of Unitary Coupled Cluster for Simulating Molecular Electronic Structure
• Differentiable Learning of Quantum Circuit Born Machine
• From transistor to trapped-ion computers for quantum chemistry
• Witnessing eigenstates for quantum simulation of Hamiltonian spectra
• Optimal Quantum Measurements of Expectation Values of Observables
• Sequential minimal optimization for quantum-classical hybrid algorithms
• Increasing the representation accuracy of quantum simulations of chemistry without extra quantum resources
• Large gradients via correlation in random parameterized quantum circuits
• Performance of hybrid quantum/classical variational heuristics for combinatorial optimization
• Application of fermionic marginal constraints to hybrid quantum algorithms
• Decoding quantum errors with subspace expansions
• Variational Quantum Unsampling on a Quantum Photonic Processor
• Universal discriminative quantum neural networks
• Adversarial quantum circuit learning for pure state approximation
• Learning to learn with quantum neural networks via classical neural networks
• Learning Unitaries by Gradient Descent
• Forward Thinking: Building and Training Neural Networks One Layer at a Time
• Accelerated variational algorithms for digital quantum simulation of many-body ground states
• A Jacobi Diagonalization and Anderson Acceleration Algorithm For Variational Quantum Algorithm Parameter Optimization

Cited by in corpus (154)

• Variational Quantum Algorithms
• Cost Function Dependent Barren Plateaus in Shallow Parametrized Quantum Circuits
• The Variational Quantum Eigensolver: a review of methods and best practices
• The power of quantum neural networks
• Noise-Induced Barren Plateaus in Variational Quantum Algorithms
• Power of data in quantum machine learning
• Connecting ansatz expressibility to gradient magnitudes and barren plateaus
• qubit-ADAPT-VQE: An adaptive algorithm for constructing hardware-efficient ansatze on a quantum processor
• A Review on Quantum Approximate Optimization Algorithm and its Variants
• Absence of Barren Plateaus in Quantum Convolutional Neural Networks
• General parameter-shift rules for quantum gradients
• Effect of barren plateaus on gradient-free optimization
• Diagnosing Barren Plateaus with Tools from Quantum Optimal Control
• Quantum Computing for High-Energy Physics: State of the Art and Challenges. Summary of the QC4HEP Working Group
• Quantum agents in the Gym: a variational quantum algorithm for deep Q-learning
• Quantum circuit architecture search for variational quantum algorithms
• Solving nonlinear differential equations with differentiable quantum circuits
• Large gradients via correlation in random parameterized quantum circuits
• Equivalence of quantum barren plateaus to cost concentration and narrow gorges
• Higher Order Derivatives of Quantum Neural Networks with Barren Plateaus
• Filtering variational quantum algorithms for combinatorial optimization
• Quantum computing models for artificial neural networks
• Neutral Atom Quantum Computing Hardware: Performance and End-User Perspective
• Quantum Machine Learning: from physics to software engineering
• Theoretical Guarantees for Permutation-Equivariant Quantum Neural Networks
• Biology and medicine in the landscape of quantum advantages
• ADAPT-VQE is insensitive to rough parameter landscapes and barren plateaus
• Layer VQE: A Variational Approach for Combinatorial Optimization on Noisy Quantum Computers
• Barren plateaus in quantum tensor network optimization
• Quantum computing of the ${}^6$Li nucleus via ordered unitary coupled clusters
• Learning quantum data with the quantum Earth Mover's distance
• Reformulation of the No-Free-Lunch Theorem for Entangled Data Sets
• Avoiding barren plateaus via transferability of smooth solutions in Hamiltonian Variational Ansatz
• Generative quantum machine learning via denoising diffusion probabilistic models
• Realizing a quantum generative adversarial network using a programmable superconducting processor
• Universal Effectiveness of High-Depth Circuits in Variational Eigenproblems
• Reflection Equivariant Quantum Neural Networks for Enhanced Image Classification
• Training Saturation in Layerwise Quantum Approximate Optimisation
• Abrupt Transitions in Variational Quantum Circuit Training
• Avoiding Barren Plateaus with Classical Deep Neural Networks
• Hybrid Classical-Quantum Autoencoder for Anomaly Detection
• Hybrid quantum ResNet for car classification and its hyperparameter optimization
• Natural Evolutionary Strategies for Variational Quantum Computation
• Detecting and quantifying entanglement on near-term quantum devices
• Toward Trainability of Quantum Neural Networks
• Variational learning for quantum artificial neural networks
• ResQNets: A Residual Approach for Mitigating Barren Plateaus in Quantum Neural Networks
• Mitigating Barren Plateaus with Transfer-learning-inspired Parameter Initializations
• Applying QNLP to sentiment analysis in finance
• Comparative study of variations in quantum approximate optimization algorithms for the Traveling Salesman Problem
• Lyapunov control-inspired strategies for quantum combinatorial optimization
• Long-time simulations with high fidelity on quantum hardware
• Trainability Enhancement of Parameterized Quantum Circuits via Reduced-Domain Parameter Initialization
• A semi-agnostic ansatz with variable structure for quantum machine learning
• Entanglement entropy production in Quantum Neural Networks
• Uncovering Instabilities in Variational-Quantum Deep Q-Networks
• Variational Quantum Linear Solver with Dynamic Ansatz
• Hamiltonian operator approximation for energy measurement and ground state preparation
• Classification of dynamical Lie algebras for translation-invariant 2-local spin systems in one dimension
• Warm-Starting and Quantum Computing: A Systematic Mapping Study
• Alleviating Barren Plateaus in Parameterized Quantum Machine Learning Circuits: Investigating Advanced Parameter Initialization Strategies
• Engineered dissipation to mitigate barren plateaus
• An evolving objective function for improved variational quantum optimisation
• Efficient variational synthesis of quantum circuits with coherent multi-start optimization
• Learning shallow quantum circuits
• On Circuit Depth Scaling For Quantum Approximate Optimization
• The Quantum Path Kernel: a Generalized Quantum Neural Tangent Kernel for Deep Quantum Machine Learning
• Reduction of finite sampling noise in quantum neural networks
• Quantum computing quantum Monte Carlo with hybrid tensor network for electronic structure calculations
• Calculating nonadiabatic couplings and Berry's phase by variational quantum eigensolvers
• Here comes the SU(N): multivariate quantum gates and gradients
• Isometric tensor network optimization for extensive Hamiltonians is free of barren plateaus
• Networked Quantum Services
• Quantum Generative Learning for High-Resolution Medical Image Generation
• An exponentially-growing family of universal quantum circuits
• Quantum Optimization for Training Quantum Neural Networks
• The Unified Effect of Data Encoding, Ansatz Expressibility and Entanglement on the Trainability of HQNNs
• Atomic Quantum Technologies for Quantum Matter and Fundamental Physics Applications
• The quantum cost function concentration dependency on the parametrization expressivity
• Improved variational quantum eigensolver via quasi-dynamical evolution
• Variational Preparation of the Sachdev-Ye-Kitaev Thermofield Double
• Evolution strategies: Application in hybrid quantum-classical neural networks
• EHA: Entanglement-variational Hardware-efficient Ansatz for Eigensolvers
• Long-lived Particles Anomaly Detection with Parametrized Quantum Circuits
• Quantum Computing and Tensor Networks for Laminate Design: A Novel Approach to Stacking Sequence Retrieval
• Iterative Layerwise Training for Quantum Approximate Optimization Algorithm
• A Parameter Setting Heuristic for the Quantum Alternating Operator Ansatz
• Randomized adaptive quantum state preparation
• Numerical hardware-efficient variational quantum simulation of a soliton solution
• Measurement-induced entanglement phase transitions in variational quantum circuits
• Variational Quantum Algorithms for Trace Distance and Fidelity Estimation
• Bayesian Learning of Parameterised Quantum Circuits
• Forecasting steam mass flow in power plants using the parallel hybrid network
• Faster variational quantum algorithms with quantum kernel-based surrogate models
• Sequential optimal selection of a single-qubit gate and its relation to barren plateau in parameterized quantum circuits
• Progress towards analytically optimal angles in quantum approximate optimisation
• Near-term Efficient Quantum Algorithms for Entanglement Analysis
• Generalization Error Bound for Quantum Machine Learning in NISQ Era -- A Survey
• Protocols for Trainable and Differentiable Quantum Generative Modelling
• Barren plateaus are swamped with traps
• Equivalence of cost concentration and gradient vanishing for quantum circuits: An elementary proof in the Riemannian formulation
• Random coordinate descent: a simple alternative for optimizing parameterized quantum circuits
• Beyond Quantum Annealing: Optimal control solutions to MaxCut problems
• Quantum-enhanced neural networks in the neural tangent kernel framework
• Performance of Particle Tracking Using a Quantum Graph Neural Network
• Information flow in parameterized quantum circuits
• Exponential Qubit Reduction in Optimization for Financial Transaction Settlement
• Mitigating Quantum Gate Errors for Variational Eigensolvers Using Hardware-Inspired Zero-Noise Extrapolation
• Machine-Learning Insights into the Entanglement-trainability Correlation of Parameterized Quantum Circuits
• Hamiltonian-based graph-state ansatz for variational quantum algorithms
• Quantum Extremal Learning
• QFCNN: Quantum Fourier Convolutional Neural Network
• Backpropagation scaling in parameterised quantum circuits
• Single entanglement connection architecture between multi-layer bipartite Hardware Efficient Ansatz
• Restricting to the chip architecture maintains the quantum neural network accuracy
• Enhancing Variational Quantum Circuit Training: An Improved Neural Network Approach for Barren Plateau Mitigation
• Sketching the Best Approximate Quantum Compiling Problem
• Reducing measurement costs by recycling the Hessian in adaptive variational quantum algorithms
• An Amplitude-Based Implementation of the Unit Step Function on a Quantum Computer
• Perturbative gadgets for gate-based quantum computing: Non-recursive constructions without subspace restrictions
• Learning to learn with an evolutionary strategy applied to variational quantum algorithms
• Leveraging commuting groups for an efficient variational Hamiltonian ansatz
• Quantum Feasibility Labeling for NP-complete Vertex Coloring Problem
• VQE-generated quantum circuit dataset for machine learning
• Almost fault-tolerant quantum machine learning with drastic overhead reduction
• An Efficient Gradient Sensitive Alternate Framework for VQE with Variable Ansatz
• Quantum-secure multiparty deep learning
• The Accuracy vs. Sampling Overhead Trade-off in Quantum Error Mitigation Using Monte Carlo-Based Channel Inversion
• Barren plateaus are amplified by the dimension of qudits
• A Universal Quantum Computer From Relativistic Motion
• Perspectives on Utilization of Measurements in Quantum Algorithms
• Expressivity of deterministic quantum computation with one qubit
• Policy Gradient Approach to Compilation of Variational Quantum Circuits
• Quantum Generative Training Using Rényi Divergences
• Adaptive Quantum Generative Training using an Unbounded Loss Function
• Empirical Power of Quantum Encoding Methods for Binary Classification
• OnionVQE Optimization Strategy for Ground State Preparation on NISQ Devices
• Orbital Expansion Variational Quantum Eigensolver: Enabling Efficient Simulation of Molecules with Shallow Quantum Circuit
• A hybrid quantum-classical neural network with deep residual learning
• Generative flow-based warm start of the variational quantum eigensolver
• Mitigating Noise-Induced Gradient Vanishing in Variational Quantum Algorithm Training
• A Cyclic Layerwise QAOA Training
• IGO-QNN: Quantum Neural Network Architecture for Inductive Grover Oracularization
• Improving Parameter Training for VQEs by Sequential Hamiltonian Assembly
• Batched Line Search Strategy for Navigating through Barren Plateaus in Quantum Circuit Training
• Quantum Machine Learning for State Tomography Using Classical Data
• Gradient Scalability and Taylor Surrogation of Quantum Cost Landscapes
• Introducing Reduced-Width QNNs, an AI-inspired Ansatz Design Pattern
• Compression of quantum shallow-circuit states
• Adaptive Interpolating Quantum Transform: A Quantum-Native Framework for Efficient Transform Learning
• Slice-Wise Initial State Optimization to Improve Cost and Accuracy of the VQE on Lattice Models
• Quantum feature-map learning with reduced resource overhead
• Performance Guarantees for Quantum Neural Estimation of Entropies
• FRQI Pairs method for image classification using Quantum Recurrent Neural Network