Theoretical Guarantees for Permutation-Equivariant Quantum Neural Networks

Abstract

Despite the great promise of quantum machine learning models, there are several challenges one must overcome before unlocking their full potential. For instance, models based on quantum neural networks (QNNs) can suffer from excessive local minima and barren plateaus in their training landscapes. Recently, the nascent field of geometric quantum machine learning (GQML) has emerged as a potential solution to some of those issues. The key insight of GQML is that one should design architectures, such as equivariant QNNs, encoding the symmetries of the problem at hand. Here, we focus on problems with permutation symmetry (i.e., the group of symmetry $S_n$), and show how to build $S_n$-equivariant QNNs. We provide an analytical study of their performance, proving that they do not suffer from barren plateaus, quickly reach overparametrization, and generalize well from small amounts of data. To verify our results, we perform numerical simulations for a graph state classification task. Our work provides the first theoretical guarantees for equivariant QNNs, thus indicating the extreme power and potential of GQML.

15+21 pages, 5 + 5 figures. Prior generalization bounds replaced with more general theorem. Comments added about hardness of simulation and narrow gorges

References in corpus (19)

• An introduction to quantum machine learning
• Multi-party entanglement in graph states
• Challenges and Opportunities in Quantum Machine Learning
• SchNet: A continuous-filter convolutional neural network for modeling quantum interactions
• Beyond Barren Plateaus: Quantum Variational Algorithms Are Swamped With Traps
• Unsupervised Machine Learning on a Hybrid Quantum Computer
• Exploiting symmetry in variational quantum machine learning
• Experimental quantum speed-up in reinforcement learning agents
• Group-Invariant Quantum Machine Learning
• ADAPT-VQE is insensitive to rough parameter landscapes and barren plateaus
• Lorentz Group Equivariant Neural Network for Particle Physics
• Avoiding barren plateaus via transferability of smooth solutions in Hamiltonian Variational Ansatz
• Building spatial symmetries into parameterized quantum circuits for faster training
• Avoiding Barren Plateaus with Classical Deep Neural Networks
• Representation Theory for Geometric Quantum Machine Learning
• Efficient classical algorithms for simulating symmetric quantum systems
• Exploiting Landscape Geometry to Enhance Quantum Optimal Control
• Inference-Based Quantum Sensing
• Symmetry Group Equivariant Architectures for Physics

Cited by in corpus (53)

• Barren Plateaus in Variational Quantum Computing
• A Lie Algebraic Theory of Barren Plateaus for Deep Parameterized Quantum Circuits
• Theory for Equivariant Quantum Neural Networks
• Does provable absence of barren plateaus imply classical simulability?
• Understanding quantum machine learning also requires rethinking generalization
• On the practical usefulness of the Hardware Efficient Ansatz
• Trainability barriers and opportunities in quantum generative modeling
• Provably Trainable Rotationally Equivariant Quantum Machine Learning
• Towards quantum computing for clinical trial design and optimization: A perspective on new opportunities and challenges
• Classification of dynamical Lie algebras for translation-invariant 2-local spin systems in one dimension
• Drastic Circuit Depth Reductions with Preserved Adversarial Robustness by Approximate Encoding for Quantum Machine Learning
• Tight and Efficient Gradient Bounds for Parameterized Quantum Circuits
• Effects of noise on the overparametrization of quantum neural networks
• Generalization of Quantum Machine Learning Models Using Quantum Fisher Information Metric
• Quantum Convolutional Neural Networks are Effectively Classically Simulable
• Lie-algebraic classical simulations for quantum computing
• Symmetry breaking in geometric quantum machine learning in the presence of noise
• On the universality of $S_n$-equivariant $k$-body gates
• VQC-Based Reinforcement Learning with Data Re-uploading: Performance and Trainability
• Non-Unitary Quantum Machine Learning
• The role of data embedding in equivariant quantum convolutional neural networks
• Reinforcement learning-based architecture search for quantum machine learning
• Splitting and Parallelizing of Quantum Convolutional Neural Networks for Learning Translationally Symmetric Data
• Symmetry-invariant quantum machine learning force fields
• Unitary Designs of Symmetric Local Random Circuits
• Variational-quantum-eigensolver-inspired optimization for spin-chain work extraction
• Image Classification with Rotation-Invariant Variational Quantum Circuits
• Adversarial Robustness Guarantees for Quantum Classifiers
• The power and limitations of learning quantum dynamics incoherently
• Variational quantum computing for quantum simulation: principles, implementations, and challenges
• SnCQA: A hardware-efficient equivariant quantum convolutional circuit architecture
• Analyzing the quantum approximate optimization algorithm: ansätze, symmetries, and Lie algebras
• Gradients and frequency profiles of quantum re-uploading models
• Trade-off between Gradient Measurement Efficiency and Expressivity in Deep Quantum Neural Networks
• All you need is spin: SU(2) equivariant variational quantum circuits based on spin networks
• Permutation-equivariant quantum convolutional neural networks
• Backpropagation scaling in parameterised quantum circuits
• High-fidelity dimer excitations using quantum hardware
• Pitfalls when tackling the exponential concentration of parameterized quantum models
• Architectures and random properties of symplectic quantum circuits
• Measurement-based quantum machine learning
• Towards Improved Quantum Machine Learning for Molecular Force Fields
• A quantum tug of war between randomness and symmetries on homogeneous spaces
• Analyzing the free states of one quantum resource theory as resource states of another
• Quantum Active Learning
• Efficient Online Quantum Circuit Learning with No Upfront Training
• Scaling of symmetry-restricted quantum circuits
• Quantum-Enhanced Neural Exchange-Correlation Functionals
• Learning complexity gradually in quantum machine learning models
• Equivalence between exponential concentration in quantum machine learning kernels and barren plateaus in variational algorithms
• LArTPC hit-based topology classification with quantum machine learning and symmetry
• TabularQGAN: A quantum generative model for tabular data synthesis
• Data Efficient Prediction of excited-state properties using Quantum Neural Networks