The Adjoint Is All You Need: Characterizing Barren Plateaus in Quantum Ansätze

Abstract

Using tools from the representation theory of compact Lie groups, we formulate a theory of Barren Plateaus (BPs) for parameterized quantum circuits whose observables lie in their dynamical Lie algebra (DLA), a setting that we term Lie algebra Supported Ansatz (LASA). A large variety of commonly used ansätze such as the Hamiltonian Variational Ansatz, Quantum Alternating Operator Ansatz, and many equivariant quantum neural networks are LASAs. In particular, our theory provides, for the first time, the ability to compute the variance of the gradient of the cost function of the quantum compound ansatz. We rigorously prove that, for LASA, the variance of the gradient of the cost function, for a 2-design of the dynamical Lie group, scales inversely with the dimension of the DLA, which agrees with existing numerical observations. In addition, to motivate the applicability of our results for 2-designs to practical settings, we show that rapid mixing occurs for LASAs with polynomial DLA. Lastly, we include potential extensions for handling cases when the observable lies outside of the DLA and the implications of our results.

References in corpus (15)

• Beyond Barren Plateaus: Quantum Variational Algorithms Are Swamped With Traps
• Diagnosing Barren Plateaus with Tools from Quantum Optimal Control
• Theory of overparametrization in quantum neural networks
• Group-Invariant Quantum Machine Learning
• Equivalence of quantum barren plateaus to cost concentration and narrow gorges
• A Lie Algebraic Theory of Barren Plateaus for Deep Parameterized Quantum Circuits
• Layer VQE: A Variational Approach for Combinatorial Optimization on Noisy Quantum Computers
• Barren plateaus in quantum tensor network optimization
• Constrained Quantum Optimization for Extractive Summarization on a Trapped-ion Quantum Computer
• Constrained Optimization via Quantum Zeno Dynamics
• Quantum Deep Hedging
• Quantum Image Segmentation Based on Grayscale Morphology
• Efficient classical algorithms for simulating symmetric quantum systems
• Critical Points in Quantum Generative Models
• Expressivity of Variational Quantum Machine Learning on the Boolean Cube

Cited by in corpus (39)

• Barren Plateaus in Variational Quantum Computing
• A Lie Algebraic Theory of Barren Plateaus for Deep Parameterized Quantum Circuits
• Does provable absence of barren plateaus imply classical simulability?
• Towards large-scale quantum optimization solvers with few qubits
• Classification of dynamical Lie algebras for translation-invariant 2-local spin systems in one dimension
• Variational quantum simulation: a case study for understanding warm starts
• Tight and Efficient Gradient Bounds for Parameterized Quantum Circuits
• Quantum Convolutional Neural Networks are Effectively Classically Simulable
• Quantum algorithms for scientific computing
• Trainability and Expressivity of Hamming-Weight Preserving Quantum Circuits for Machine Learning
• Non-Unitary Quantum Machine Learning
• Constrained and Vanishing Expressivity of Quantum Fourier Models
• Image Classification with Rotation-Invariant Variational Quantum Circuits
• Barren plateaus are swamped with traps
• Toward hybrid quantum simulations with qubits and qumodes on trapped-ion platforms
• Variational quantum computing for quantum simulation: principles, implementations, and challenges
• Adversarial Robustness Guarantees for Quantum Classifiers
• State preparation of lattice field theories using quantum optimal control
• Analyzing the quantum approximate optimization algorithm: ansätze, symmetries, and Lie algebras
• Equivariant Variational Quantum Eigensolver to detect Phase Transitions through Energy Level Crossings
• Trade-off between Gradient Measurement Efficiency and Expressivity in Deep Quantum Neural Networks
• Efficient quantum-enhanced classical simulation for patches of quantum landscapes
• QSlack: A slack-variable approach for variational quantum semi-definite programming
• Scalability Challenges in Variational Quantum Optimization under Stochastic Noise
• Backpropagation scaling in parameterised quantum circuits
• Imaginary Hamiltonian variational ansatz for combinatorial optimization problems
• Non-Iterative Disentangled Unitary Coupled-Cluster based on Lie-algebraic structure
• Dual-VQE: A quantum algorithm to lower bound the ground-state energy
• Pitfalls when tackling the exponential concentration of parameterized quantum models
• Exact spectral gaps of random one-dimensional quantum circuits
• Architectures and random properties of symplectic quantum circuits
• Counterdiabatic ADAPT-VQE for molecular simulation
• Non-Universality from Conserved Superoperators in Unitary Circuits
• Estimates of loss function concentration in noisy parametrized quantum circuits
• Exploiting many-body localization for scalable variational quantum simulation
• A graph-theoretic approach to chaos and complexity in quantum systems
• Natural gradient and parameter estimation for quantum Boltzmann machines
• Moments of Quantum Channel Ensembles
• Non-Markovian Noise in Symmetry-Preserving Quantum Dynamics