A Lie Algebraic Theory of Barren Plateaus for Deep Parameterized Quantum Circuits

Abstract

Variational quantum computing schemes train a loss function by sending an initial state through a parametrized quantum circuit, and measuring the expectation value of some operator. Despite their promise, the trainability of these algorithms is hindered by barren plateaus (BPs) induced by the expressiveness of the circuit, the entanglement of the input data, the locality of the observable, or the presence of noise. Up to this point, these sources of BPs have been regarded as independent. In this work, we present a general Lie algebraic theory that provides an exact expression for the variance of the loss function of sufficiently deep parametrized quantum circuits, even in the presence of certain noise models. Our results allow us to understand under one framework all aforementioned sources of BPs. This theoretical leap resolves a standing conjecture about a connection between loss concentration and the dimension of the Lie algebra of the circuit's generators.

11+17 pages, 2+2 figures, updated manuscript and title to published version

References in corpus (37)

• Variational Quantum Algorithms
• A Quantum Approximate Optimization Algorithm
• Noisy intermediate-scale quantum (NISQ) algorithms
• An introduction to quantum machine learning
• Connecting ansatz expressibility to gradient magnitudes and barren plateaus
• Hybrid quantum-classical algorithms and quantum error mitigation
• Training variational quantum algorithms is NP-hard
• Absence of Barren Plateaus in Quantum Convolutional Neural Networks
• Beyond Barren Plateaus: Quantum Variational Algorithms Are Swamped With Traps
• Diagnosing Barren Plateaus with Tools from Quantum Optimal Control
• Trainability of Dissipative Perceptron-Based Quantum Neural Networks
• Theory of overparametrization in quantum neural networks
• Equivalence of quantum barren plateaus to cost concentration and narrow gorges
• Entanglement Devised Barren Plateau Mitigation
• Barren plateaus preclude learning scramblers
• On barren plateaus and cost function locality in variational quantum algorithms
• Theoretical Guarantees for Permutation-Equivariant Quantum Neural Networks
• ADAPT-VQE is insensitive to rough parameter landscapes and barren plateaus
• Barren plateaus in quantum tensor network optimization
• Analyzing the barren plateau phenomenon in training quantum neural networks with the ZX-calculus
• Restrictions on realizable unitary operations imposed by symmetry and locality
• On the practical usefulness of the Hardware Efficient Ansatz
• Variational Quantum Eigensolver for Frustrated Quantum Systems
• The Adjoint Is All You Need: Characterizing Barren Plateaus in Quantum Ansätze
• Fixed Depth Hamiltonian Simulation via Cartan Decomposition
• The Presence and Absence of Barren Plateaus in Tensor-network Based Machine Learning
• Progress toward favorable landscapes in quantum combinatorial optimization
• Absence of barren plateaus in finite local-depth circuits with long-range entanglement
• Effects of noise on the overparametrization of quantum neural networks
• Efficient estimation of trainability for variational quantum circuits
• Isometric tensor network optimization for extensive Hamiltonians is free of barren plateaus
• The quantum cost function concentration dependency on the parametrization expressivity
• Barren plateaus from learning scramblers with local cost functions
• On the universality of $S_n$-equivariant $k$-body gates
• F-Divergences and Cost Function Locality in Generative Modelling with Quantum Circuits
• Showcasing a Barren Plateau Theory Beyond the Dynamical Lie Algebra
• Quantifying the barren plateau phenomenon for a model of unstructured variational ansätze

Cited by in corpus (79)

• Barren Plateaus in Variational Quantum Computing
• Does provable absence of barren plateaus imply classical simulability?
• The Adjoint Is All You Need: Characterizing Barren Plateaus in Quantum Ansätze
• Quantum Machine Learning in Drug Discovery: Applications in Academia and Pharmaceutical Industries
• Towards large-scale quantum optimization solvers with few qubits
• On fundamental aspects of quantum extreme learning machines
• 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
• Computing exact moments of local random quantum circuits via tensor networks
• Quantum algorithms for scientific computing
• Trainability and Expressivity of Hamming-Weight Preserving Quantum Circuits for Machine Learning
• Taming quantum systems: A tutorial for using shortcuts-to-adiabaticity, quantum optimal control, and reinforcement learning
• Neural quantum kernels: training quantum kernels with quantum neural networks
• Non-Unitary Quantum Machine Learning
• Boundary Treatment for Variational Quantum Simulations of Partial Differential Equations on Quantum Computers
• Constrained and Vanishing Expressivity of Quantum Fourier Models
• Opportunities and challenges of quantum computing for climate modelling
• Symmetry-informed transferability of optimal parameters in the Quantum Approximate Optimization Algorithm
• Reinforcement learning-based architecture search for quantum machine learning
• Early Fault-Tolerant Quantum Algorithms in Practice: Application to Ground-State Energy Estimation
• Symmetry-invariant quantum machine learning force fields
• Barren plateaus are swamped with traps
• Toward hybrid quantum simulations with qubits and qumodes on trapped-ion platforms
• Image Classification with Rotation-Invariant Variational Quantum Circuits
• Variational quantum computing for quantum simulation: principles, implementations, and challenges
• Quantum continual learning on a programmable superconducting processor
• Advancing quantum simulations of nuclear shell model with noise-resilient protocols
• Adversarial Robustness Guarantees for Quantum Classifiers
• Equivariant Variational Quantum Eigensolver to detect Phase Transitions through Energy Level Crossings
• State preparation of lattice field theories using quantum optimal control
• Analyzing the quantum approximate optimization algorithm: ansätze, symmetries, and Lie algebras
• Quantum neural compressive sensing for ghost imaging
• Scalability Challenges in Variational Quantum Optimization under Stochastic Noise
• Quantum encoder for fixed Hamming-weight subspaces
• QSlack: A slack-variable approach for variational quantum semi-definite programming
• Efficient quantum-enhanced classical simulation for patches of quantum landscapes
• Trade-off between Gradient Measurement Efficiency and Expressivity in Deep Quantum Neural Networks
• Backpropagation scaling in parameterised quantum circuits
• On the similarity of bandwidth-tuned quantum kernels and classical kernels
• Imaginary Hamiltonian variational ansatz for combinatorial optimization problems
• Non-Iterative Disentangled Unitary Coupled-Cluster based on Lie-algebraic structure
• Architectures and random properties of symplectic quantum circuits
• Exact spectral gaps of random one-dimensional quantum circuits
• Pitfalls when tackling the exponential concentration of parameterized quantum models
• Dual-VQE: A quantum algorithm to lower bound the ground-state energy
• Measurement-based quantum machine learning
• Expressibility, entangling power and quantum average causal effect for causally indefinite circuits
• Quantitative convergence of trained quantum neural networks to a Gaussian process
• The Lie Algebra of XY-mixer Topologies and Warm Starting QAOA for Constrained Optimization
• Toward scalable quantum computations of atomic nuclei
• Perspectives on Utilization of Measurements in Quantum Algorithms
• On the Differential Topology of Expressivity of Parameterized Quantum Circuits
• Non-Universality from Conserved Superoperators in Unitary Circuits
• Quantum-data-driven dynamical transition in quantum learning
• Exploiting many-body localization for scalable variational quantum simulation
• Counterdiabatic ADAPT-VQE for molecular simulation
• Estimates of loss function concentration in noisy parametrized quantum circuits
• A variational quantum algorithm for entanglement quantification
• Digitized Counter-Diabatic Quantum Optimization for Bin Packing Problem
• Symmetry-enhanced Counterdiabatic Quantum Algorithm for Qudits
• Feasibility of performing quantum chemistry calculations on quantum computers
• Lie groups for quantum complexity and barren plateau theory
• Cheaper and more noise-resilient quantum state preparation using eigenvector continuation
• SQL2Circuits: Estimating Cardinalities, Execution Times, and Costs for SQL Queries with Quantum Natural Language Processing
• Hybrid Quantum-Classical Clustering for Preparing a Prior Distribution of Eigenspectrum
• Learning complexity gradually in quantum machine learning models
• A graph-theoretic approach to chaos and complexity in quantum systems
• Natural gradient and parameter estimation for quantum Boltzmann machines
• Direct Gradient Computation for Barren Plateaus in Parameterized Quantum Circuits
• Quantum reservoir computing for predicting and characterizing chaotic maps
• Optimizing Unitary Coupled Cluster Wave Functions on Quantum Hardware: Error Bound and Resource-Efficient Optimizer
• Quantum simulation of massive Thirring and Gross--Neveu models for arbitrary number of flavors
• Variational Quantum Generative Modeling by Sampling Expectation Values of Tunable Observables
• Exploiting biased noise in variational quantum models
• Non-Markovian Noise in Symmetry-Preserving Quantum Dynamics
• Moments of Quantum Channel Ensembles
• Variational decision diagrams for quantum-inspired machine learning applications