Group-Invariant… (2022-05-04T00:00:00.000000Z)

TL;DR

This work presents a simple, yet powerful, framework where the underlying invariances in the data are used to build QML models that, by construction, respect those symmetries that remain invariant under the action of any element of the symmetry group G associated to the dataset.

Abstract

Quantum Machine Learning (QML) models are aimed at learning from data encoded in quantum states. Recently, it has been shown that models with little to no inductive biases (i.e., with no assumptions about the problem embedded in the model) are likely to have trainability and generalization issues, especially for large problem sizes. As such, it is fundamental to develop schemes that encode as much information as available about the problem at hand. In this work we present a simple, yet powerful, framework where the underlying invariances in the data are used to build QML models that, by construction, respect those symmetries. These so-called group-invariant models produce outputs that remain invariant under the action of any element of the symmetry group G associated to the dataset. We present theoretical results underpinning the design of G -invariant models, and exemplify their application through several paradigmatic QML classiﬁcation tasks including cases when G is a continuous Lie group and also when it is a discrete symmetry group. Notably, our framework allows us to recover, in an elegant way, several well known algorithms for the literature, as well as to discover new ones. Taken together, we expect that our results will help pave the way towards a more geometric and group-theoretic approach to QML model design.

Authors

Guillaume Verdon

2 papers

Patrick J. Coles

4 papers

Martín Larocca

1 papers

TL;DR

Abstract

Authors

References108 items

Building spatial symmetries into parameterized quantum circuits for faster training

The randomized measurement toolbox

Detecting Entanglement in Quantum Many-Body Systems via Permutation Moments.

Symmetry Group Equivariant Architectures for Physics

Speeding up Learning Quantum States through Group Equivariant Convolutional Quantum Ans{ä}tze

Quantum advantage in learning from experiments

Revisiting dequantization and quantum advantage in learning tasks

Exponential Separations Between Learning With and Without Quantum Memory

Generalization in quantum machine learning from few training data

Subtleties in the trainability of quantum machine learning models

Theory of overparametrization in quantum neural networks

Quantum algorithms for group convolution, cross-correlation, and equivariant transformations

Entangled Datasets for Quantum Machine Learning

Provably efficient machine learning for quantum many-body problems

Diagnosing Barren Plateaus with Tools from Quantum Optimal Control

Covariant quantum kernels for data with group structure

Progress toward favorable landscapes in quantum combinatorial optimization

Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges

Computable and Operationally Meaningful Multipartite Entanglement Measures.

Equivalence of quantum barren plateaus to cost concentration and narrow gorges

Cost function dependent barren plateaus in shallow parametrized quantum circuits

Sub-quantum Fisher information

Quantum algorithmic measurement

Connecting ansatz expressibility to gradient magnitudes and barren plateaus

Variational quantum algorithms

Absence of Barren Plateaus in Quantum Convolutional Neural Networks

Variational quantum algorithm for estimating the quantum Fisher information

The controlled SWAP test for determining quantum entanglement

Trainability of Dissipative Perceptron-Based Quantum Neural Networks

Large gradients via correlation in random parameterized quantum circuits

Discriminating nonisomorphic graphs with an experimental quantum annealer

Variational quantum state eigensolver

One-body entanglement as a quantum resource in fermionic systems

Cost-Function-Dependent Barren Plateaus in Shallow Quantum Neural Networks

qubit-ADAPT-VQE: An adaptive algorithm for constructing hardware-efficient ansatze on a quantum processor

Quantum Cryptography

Quantum Hamiltonian-Based Models and the Variational Quantum Thermalizer Algorithm

Quantum Graph Neural Networks

Efficient symmetry-preserving state preparation circuits for the variational quantum eigensolver algorithm

An initialization strategy for addressing barren plateaus in parametrized quantum circuits

Training of quantum circuits on a hybrid quantum computer

Quantum convolutional neural networks

The Principia : Mathematical Principles of Natural Philosophy

Quantum-enhanced sensing using non-classical spin states of a highly magnetic atom

Relational inductive biases, deep learning, and graph networks

Roto-Translation Covariant Convolutional Networks for Medical Image Analysis

Barren plateaus in quantum neural network training landscapes

Learning the quantum algorithm for state overlap

On the Generalization of Equivariance and Convolution in Neural Networks to the Action of Compact Groups

From the Quantum Approximate Optimization Algorithm to a Quantum Alternating Operator Ansatz

Asymptotic properties of entanglement polytopes for large number of qubits

Bipartite entanglement in fermion systems

Hardware-efficient variational quantum eigensolver for small molecules and quantum magnets

Quantum autoencoders for efficient compression of quantum data

Quantum machine learning

Generalized concurrence measure for faithful quantification of multiparticle pure state entanglement using Lagrange’s identity and wedge product

Group Equivariant Convolutional Networks

Graph isomorphism in quasipolynomial time [extended abstract]

Progress towards practical quantum variational algorithms

Symmetry criteria for quantum simulability of effective interactions

Experimental quantum annealing: case study involving the graph isomorphism problem

A Quantum Approximate Optimization Algorithm

Graph isomorphism and adiabatic quantum computing

Critical sets of the total variance can detect all stochastic local operations and classical communication classes of multiparticle entanglement

Convexity of momentum map, Morse index, and quantum entanglement

Entanglement Polytopes: Multiparticle Entanglement from Single-Particle Information

Quantum Computation and Quantum Information

Solving the Graph Isomorphism Problem with a Quantum Annealer

Symbolic integration with respect to the Haar measure on the unitary groups

Symmetry principles in quantum systems theory

Symmetry, Representations, and Invariants

Unital Quantum Channels – Convex Structure and Revivals of Birkhoff’s Theorem

Entanglement and the power of one qubit

Decoherence and multipartite entanglement.

Integration with Respect to the Haar Measure on Unitary, Orthogonal and Symplectic Group

An observable measure of entanglement for pure states of multi-qubit systems