Theory for Equivariant Quantum Neural Networks

Abstract

Quantum neural network architectures that have little-to-no inductive biases are known to face trainability and generalization issues. Inspired by a similar problem, recent breakthroughs in machine learning address this challenge by creating models encoding the symmetries of the learning task. This is materialized through the usage of equivariant neural networks whose action commutes with that of the symmetry. In this work, we import these ideas to the quantum realm by presenting a comprehensive theoretical framework to design equivariant quantum neural networks (EQNN) for essentially any relevant symmetry group. We develop multiple methods to construct equivariant layers for EQNNs and analyze their advantages and drawbacks. Our methods can find unitary or general equivariant quantum channels efficiently even when the symmetry group is exponentially large or continuous. As a special implementation, we show how standard quantum convolutional neural networks (QCNN) can be generalized to group-equivariant QCNNs where both the convolution and pooling layers are equivariant to the symmetry group. We then numerically demonstrate the effectiveness of a SU(2)-equivariant QCNN over symmetry-agnostic QCNN on a classification task of phases of matter in the bond-alternating Heisenberg model. Our framework can be readily applied to virtually all areas of quantum machine learning. Lastly, we discuss about how symmetry-informed models such as EQNNs provide hopes to alleviate central challenges such as barren plateaus, poor local minima, and sample complexity.

26+21 pages, 12 + 2 figures; journal version with new numerics section

References in corpus (39)

• Variational Quantum Algorithms
• An introduction to quantum machine learning
• Power of data in quantum machine learning
• Challenges and Opportunities in Quantum Machine Learning
• The quest for a Quantum Neural Network
• Connecting ansatz expressibility to gradient magnitudes and barren plateaus
• A rigorous and robust quantum speed-up in supervised machine learning
• Quantum advantage in learning from experiments
• Generalization in quantum machine learning from few training data
• Training variational quantum algorithms is NP-hard
• Absence of Barren Plateaus in Quantum Convolutional Neural Networks
• Provably efficient machine learning for quantum many-body problems
• Effect of barren plateaus on gradient-free optimization
• Beyond Barren Plateaus: Quantum Variational Algorithms Are Swamped With Traps
• Diagnosing Barren Plateaus with Tools from Quantum Optimal Control
• Exploiting symmetry in variational quantum machine learning
• Experimental quantum speed-up in reinforcement learning agents
• Theory of overparametrization in quantum neural networks
• Efficient Quantum Circuits for Schur and Clebsch-Gordan Transforms
• Group-Invariant Quantum Machine Learning
• Generalization in Quantum Machine Learning: a Quantum Information Perspective
• 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
• Quantum Assisted Simulator
• Computable and operationally meaningful multipartite entanglement measures
• Direct prediction of phonon density of states with Euclidean neural networks
• The Weingarten Calculus
• Speeding up Learning Quantum States through Group Equivariant Convolutional Quantum Ansätze
• Reflection Equivariant Quantum Neural Networks for Enhanced Image Classification
• Efficient algorithm for multi-qudit twirling for ensemble quantum computation
• Non-trivial symmetries in quantum landscapes and their resilience to quantum noise
• Near-optimal covariant quantum error-correcting codes from random unitaries with symmetries
• Quantum Channels and Representation Theory
• Factorization and criticality in finite XXZ systems of arbitrary spin
• Programmability of covariant quantum channels
• Group-covariant extreme and quasi-extreme channels

Cited by in corpus (42)

• Barren Plateaus in Variational Quantum Computing
• Quantum Computing for High-Energy Physics: State of the Art and Challenges. Summary of the QC4HEP Working Group
• Does provable absence of barren plateaus imply classical simulability?
• On the practical usefulness of the Hardware Efficient Ansatz
• Trainability barriers and opportunities in quantum generative modeling
• Provably Trainable Rotationally Equivariant Quantum Machine Learning
• Generalization of Quantum Machine Learning Models Using Quantum Fisher Information Metric
• Quantum Convolutional Neural Networks are Effectively Classically Simulable
• Quantum algorithms for scientific computing
• Symmetry breaking in geometric quantum machine learning in the presence of noise
• On the universality of $S_n$-equivariant $k$-body gates
• The role of data embedding in equivariant quantum convolutional neural networks
• Reinforcement learning-based architecture search for quantum machine learning
• Machine Learning for Estimation and Control of Quantum Systems
• Theory of Quantum Circuits with Abelian Symmetries
• Enabling High Performance Debugging for Variational Quantum Algorithms using Compressed Sensing
• Symmetry-invariant quantum machine learning force fields
• Unitary Designs of Symmetric Local Random Circuits
• Image Classification with Rotation-Invariant Variational Quantum Circuits
• Toward Super-polynomial Quantum Speedup of Equivariant Quantum Algorithms with SU($d$) Symmetry
• Geometric Quantum Machine Learning with Horizontal Quantum Gates
• Lorentz-Equivariant Quantum Graph Neural Network for High-Energy Physics
• All you need is spin: SU(2) equivariant variational quantum circuits based on spin networks
• Trade-off between Gradient Measurement Efficiency and Expressivity in Deep Quantum Neural Networks
• High-fidelity dimer excitations using quantum hardware
• Permutation-equivariant quantum convolutional neural networks
• Imaginary Hamiltonian variational ansatz for combinatorial optimization problems
• Backpropagation scaling in parameterised quantum circuits
• Architectures and random properties of symplectic quantum circuits
• Learning Equivariant Maps with Variational Quantum Circuits
• The Lie Algebra of XY-mixer Topologies and Warm Starting QAOA for Constrained Optimization
• Analyzing the free states of one quantum resource theory as resource states of another
• A quantum tug of war between randomness and symmetries on homogeneous spaces
• SU(d)-Symmetric Random Unitaries: Quantum Scrambling, Error Correction, and Machine Learning
• Quantum Active Learning
• Towards Improved Quantum Machine Learning for Molecular Force Fields
• Scaling of symmetry-restricted quantum circuits
• Guided Graph Compression for Quantum Graph Neural Networks
• Performance Guarantees for Quantum Neural Estimation of Entropies
• 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
• Construction of Metaplectic Representations of $S{L}_2({\mathbb{Z}}_{2^n})$ and Twisted Magnetic Translations