Analyzing the barren plateau phenomenon in training quantum neural networks with the ZX-calculus

Abstract

In this paper, we propose a general scheme to analyze the gradient vanishing phenomenon, also known as the barren plateau phenomenon, in training quantum neural networks with the ZX-calculus. More precisely, we extend the barren plateaus theorem from unitary 2-design circuits to any parameterized quantum circuits under certain reasonable assumptions. The main technical contribution of this paper is representing certain integrations as ZX-diagrams and computing them with the ZX-calculus. The method is used to analyze four concrete quantum neural networks with different structures. It is shown that, for the hardware efficient ansatz and the MPS-inspired ansatz, there exist barren plateaus, while for the QCNN ansatz and the tree tensor network ansatz, there exists no barren plateau.

References in corpus (37)

• Quantum Computing in the NISQ era and beyond
• 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
• Matrix Product States, Projected Entangled Pair States, and variational renormalization group methods for quantum spin systems
• Quantum Chemistry in the Age of Quantum Computing
• Quantum Convolutional Neural Networks
• Parameterized quantum circuits as machine learning models
• Cost Function Dependent Barren Plateaus in Shallow Parametrized Quantum Circuits
• Evaluating analytic gradients on quantum hardware
• Circuit-centric quantum classifiers
• Quantum algorithms for quantum chemistry and quantum materials science
• Quantum Approximate Optimization Algorithm: Performance, Mechanism, and Implementation on Near-Term Devices
• Connecting ansatz expressibility to gradient magnitudes and barren plateaus
• Quantum generative adversarial learning
• Quantum Natural Gradient
• An initialization strategy for addressing barren plateaus in parametrized quantum circuits
• Hierarchical quantum classifiers
• Interacting Quantum Observables: Categorical Algebra and Diagrammatics
• Differentiable Learning of Quantum Circuit Born Machine
• Unsupervised Generative Modeling Using Matrix Product States
• Graph-theoretic Simplification of Quantum Circuits with the ZX-calculus
• Sequential minimal optimization for quantum-classical hybrid algorithms
• Estimating the gradient and higher-order derivatives on quantum hardware
• Variational Quantum Eigensolver with Fewer Qubits
• Large gradients via correlation in random parameterized quantum circuits
• Reducing T-count with the ZX-calculus
• Entanglement Devised Barren Plateau Mitigation
• An Adaptive Optimizer for Measurement-Frugal Variational Algorithms
• The ZX-calculus is complete for stabilizer quantum mechanics
• Phase Gadget Synthesis for Shallow Circuits
• The ZX calculus is a language for surface code lattice surgery
• There and back again: A circuit extraction tale
• Making the stabilizer ZX-calculus complete for scalars
• Effective Compression of Quantum Braided Circuits Aided by ZX-Calculus
• Completeness of the ZX-Calculus

Cited by in corpus (53)

• Diagnosing Barren Plateaus with Tools from Quantum Optimal Control
• Barren Plateaus in Variational Quantum Computing
• Trainability of Dissipative Perceptron-Based Quantum Neural Networks
• A Lie Algebraic Theory of Barren Plateaus for Deep Parameterized Quantum Circuits
• Quantum Machine Learning: from physics to software engineering
• Recent advances for quantum classifiers
• The Variational Power of Quantum Circuit Tensor Networks
• Does provable absence of barren plateaus imply classical simulability?
• Barren plateaus in quantum tensor network optimization
• Subtleties in the trainability of quantum machine learning models
• Learning quantum data with the quantum Earth Mover's distance
• Analytic theory for the dynamics of wide quantum neural networks
• The Presence and Absence of Barren Plateaus in Tensor-network Based Machine Learning
• Variational inference with a quantum computer
• Benchmarking simulated and physical quantum processing units using quantum and hybrid algorithms
• Trainability barriers and opportunities in quantum generative modeling
• Mitigating Barren Plateaus with Transfer-learning-inspired Parameter Initializations
• Tensor networks for quantum machine learning
• Absence of barren plateaus in finite local-depth circuits with long-range entanglement
• Trainability Enhancement of Parameterized Quantum Circuits via Reduced-Domain Parameter Initialization
• A semi-agnostic ansatz with variable structure for quantum machine learning
• Nonlinear dynamics as a ground-state solution on quantum computers
• Quantum Capsule Networks
• Tight and Efficient Gradient Bounds for Parameterized Quantum Circuits
• Efficient estimation of trainability for variational quantum circuits
• Quantum Convolutional Neural Networks are Effectively Classically Simulable
• Classical Splitting of Parametrized Quantum Circuits
• Isometric tensor network optimization for extensive Hamiltonians is free of barren plateaus
• Tensor networks for quantum computing
• Variational quantum algorithm for ergotropy estimation in quantum many-body batteries
• An exponentially-growing family of universal quantum circuits
• Assessing and Advancing the Potential of Quantum Computing: A NASA Case Study
• Barren plateaus from learning scramblers with local cost functions
• Improved variational quantum eigensolver via quasi-dynamical evolution
• How to Sum and Exponentiate Hamiltonians in ZXW Calculus
• Emergence of noise-induced barren plateaus in arbitrary layered noise models
• Generalization Error Bound for Quantum Machine Learning in NISQ Era -- A Survey
• Absence of barren plateaus and scaling of gradients in the energy optimization of isometric tensor network states
• The Qupit Stabiliser ZX-travaganza: Simplified Axioms, Normal Forms and Graph-Theoretic Simplification
• Deconstructing the Calculus of Relations with Tape Diagrams
• Speedy Contraction of ZX Diagrams with Triangles via Stabiliser Decompositions
• Diagrammatic Analysis for Parameterized Quantum Circuits
• Application of Quantum Tensor Networks for Protein Classification
• Supervised Learning Guarantee for Quantum AdaBoost
• Differentiating and Integrating ZX Diagrams with Applications to Quantum Machine Learning
• Quantum Extremal Learning
• Channel Attention for Quantum Convolutional Neural Networks
• Data-Dependent Generalization Bounds for Parameterized Quantum Models Under Noise
• Optimized numerical gradient and Hessian estimation for variational quantum algorithms
• Quantum circuits for partial differential equations in Fourier space
• Hybrid Quantum Classical Graph Neural Networks for Particle Track Reconstruction
• Exploiting many-body localization for scalable variational quantum simulation
• Qubit frugal entanglement determination with the deep multi-scale entanglement renormalization ansatz