Barren plateaus preclude learning scramblers

Abstract

Scrambling processes, which rapidly spread entanglement through many-body quantum systems, are difficult to investigate using standard techniques, but are relevant to quantum chaos and thermalization. In this Letter, we ask if quantum machine learning (QML) could be used to investigate such processes. We prove a no-go theorem for learning an unknown scrambling process with QML, showing that any variational ansatz is highly probable to have a barren plateau landscape, i.e., cost gradients that vanish exponentially in the system size. This implies that the required resources scale exponentially even when strategies to avoid such scaling (e.g., from ansatz-based barren plateaus or No-Free-Lunch theorems) are employed. Furthermore, we numerically and analytically extend our results to approximate scramblers. Hence, our work places generic limits on the learnability of unitaries when lacking prior information.

5 pages, 3 figures in the main text. 6 pages, 1 figure in the supplementary information. Comments welcome

References in corpus (17)

• A Quantum Approximate Optimization Algorithm
• Black holes as mirrors: quantum information in random subsystems
• Cost Function Dependent Barren Plateaus in Shallow Parametrized Quantum Circuits
• Noise-Induced Barren Plateaus in Variational Quantum Algorithms
• Chaos, Complexity, and Random Matrices
• Jarzynski-like equality for the out-of-time-ordered correlator
• Large gradients via correlation in random parameterized quantum circuits
• Variational Quantum State Eigensolver
• Scrambling in Random Unitary Circuits: Exact Results
• Learning to learn with quantum neural networks via classical neural networks
• Efficient decoding for the Hayden-Preskill protocol
• Reformulation of the No-Free-Lunch Theorem for Entangled Data Sets
• Minimal Model for Fast Scrambling
• Observation of thermalization and information scrambling in a superconducting quantum processor
• Variational Hamiltonian Diagonalization for Dynamical Quantum Simulation
• Recovery of Damaged Information and the Out-of-Time-Ordered Correlators
• No Free Lunch for Quantum Machine Learning

Cited by in corpus (83)

• Variational Quantum Algorithms
• Challenges and Opportunities in Quantum Machine Learning
• Connecting ansatz expressibility to gradient magnitudes and barren plateaus
• Generalization in quantum machine learning from few training data
• Absence of Barren Plateaus in Quantum Convolutional Neural Networks
• Effect of barren plateaus on gradient-free optimization
• Diagnosing Barren Plateaus with Tools from Quantum Optimal Control
• Barren Plateaus in Variational Quantum Computing
• Quantum Computing for High-Energy Physics: State of the Art and Challenges. Summary of the QC4HEP Working Group
• Theory of overparametrization in quantum neural networks
• Equivalence of quantum barren plateaus to cost concentration and narrow gorges
• A Lie Algebraic Theory of Barren Plateaus for Deep Parameterized Quantum Circuits
• Entanglement Devised Barren Plateau Mitigation
• Higher Order Derivatives of Quantum Neural Networks with Barren Plateaus
• Theory for Equivariant Quantum Neural Networks
• Recent advances for quantum classifiers
• Theoretical Guarantees for Permutation-Equivariant Quantum Neural Networks
• Layer VQE: A Variational Approach for Combinatorial Optimization on Noisy Quantum Computers
• Variational Quantum Algorithm for Estimating the Quantum Fisher Information
• Enhancing Generative Models via Quantum Correlations
• Does provable absence of barren plateaus imply classical simulability?
• Towards adiabatic quantum computing using compressed quantum circuits
• Subtleties in the trainability of quantum machine learning models
• Resource theory of quantum scrambling
• The Presence and Absence of Barren Plateaus in Tensor-network Based Machine Learning
• Can Error Mitigation Improve Trainability of Noisy Variational Quantum Algorithms?
• Imaginary components of out-of-time correlators and information scrambling for navigating the learning landscape of a quantum machine learning model
• Trainability barriers and opportunities in quantum generative modeling
• Transitions in Entanglement Complexity in Random Circuits
• Learning efficient decoders for quasi-chaotic quantum scramblers
• Absence of barren plateaus in finite local-depth circuits with long-range entanglement
• Long-time simulations with high fidelity on quantum hardware
• Dynamical simulation via quantum machine learning with provable generalization
• Non-trivial symmetries in quantum landscapes and their resilience to quantum noise
• A semi-agnostic ansatz with variable structure for quantum machine learning
• Quantum Mixed State Compiling
• Benchmarking Information Scrambling
• On fundamental aspects of quantum extreme learning machines
• Entangled Datasets for Quantum Machine Learning
• Quantum Capsule Networks
• Quantum algorithms from fluctuation theorems: Thermal-state preparation
• Variational quantum simulation: a case study for understanding warm starts
• Retrieving information from a black hole using quantum machine learning
• Analytical solution for nonadiabatic quantum annealing to arbitrary Ising spin Hamiltonian
• Optimal training of variational quantum algorithms without barren plateaus
• Learning shallow quantum circuits
• Variational quantum algorithm for unconstrained black box binary optimization: Application to feature selection
• Efficient estimation of trainability for variational quantum circuits
• Quantum neural networks form Gaussian processes
• Solution of SAT Problems with the Adaptive-Bias Quantum Approximate Optimization Algorithm
• Quantum algorithms for scientific computing
• Barren plateaus from learning scramblers with local cost functions
• Quantum Advantage Seeker with Kernels (QuASK): a software framework to speed up the research in quantum machine learning
• Quantifying scrambling in quantum neural networks
• Quantum simulation of operator spreading in the chaotic Ising model
• Unraveling the emergence of quantum state designs in systems with symmetry
• Experimental Quantum Learning of a Spectral Decomposition
• Large-scale simulations of Floquet physics on near-term quantum computers
• Resource frugal optimizer for quantum machine learning
• Image Classification with Rotation-Invariant Variational Quantum Circuits
• Quantum-enhanced neural networks in the neural tangent kernel framework
• Adversarial Robustness Guarantees for Quantum Classifiers
• Adaptive shot allocation for fast convergence in variational quantum algorithms
• Quantum optimal control in quantum technologies. Strategic report on current status, visions and goals for research in Europe
• QSlack: A slack-variable approach for variational quantum semi-definite programming
• Machine-Learning Insights into the Entanglement-trainability Correlation of Parameterized Quantum Circuits
• Efficient quantum-enhanced classical simulation for patches of quantum landscapes
• Quantum Extremal Learning
• Learning unitaries with quantum statistical queries
• Estimating Eigenenergies from Quantum Dynamics: A Unified Noise-Resilient Measurement-Driven Approach
• Universal compiling and (No-)Free-Lunch theorems for continuous variable quantum learning
• Learning Fourier series with parametrized quantum circuits
• Pitfalls when tackling the exponential concentration of parameterized quantum models
• Policy Gradient Approach to Compilation of Variational Quantum Circuits
• Ground state energy and magnetization curve of a frustrated magnetic system from real-time evolution on a digital quantum processor
• The Dual Role of Low-Weight Pauli Propagation: A Flawed Simulator but a Powerful Initializer for Variational Quantum Algorithms
• Optimal quantum reservoir learning in proximity to universality
• Batched Line Search Strategy for Navigating through Barren Plateaus in Quantum Circuit Training
• A coherent approach to quantum-classical optimization
• Fast suppression of classification error in variational quantum circuits
• Direct Gradient Computation for Barren Plateaus in Parameterized Quantum Circuits
• Quantum Algorithms for Unsupervised Machine Learning and Neural Networks
• Equivalence between exponential concentration in quantum machine learning kernels and barren plateaus in variational algorithms