Representation Theory for Geometric Quantum Machine Learning
read the original abstract
Recent advances in classical machine learning have shown that creating models with inductive biases encoding the symmetries of a problem can greatly improve performance. Importation of these ideas, combined with an existing rich body of work at the nexus of quantum theory and symmetry, has given rise to the field of Geometric Quantum Machine Learning (GQML). Following the success of its classical counterpart, it is reasonable to expect that GQML will play a crucial role in developing problem-specific and quantum-aware models capable of achieving a computational advantage. Despite the simplicity of the main idea of GQML -- create architectures respecting the symmetries of the data -- its practical implementation requires a significant amount of knowledge of group representation theory. We present an introduction to representation theory tools from the optics of quantum learning, driven by key examples involving discrete and continuous groups. These examples are sewn together by an exposition outlining the formal capture of GQML symmetries via "label invariance under the action of a group representation", a brief (but rigorous) tour through finite and compact Lie group representation theory, a reexamination of ubiquitous tools like Haar integration and twirling, and an overview of some successful strategies for detecting symmetries.
This paper has not been read by Pith yet.
Forward citations
Cited by 13 Pith papers
-
Enabling Lie-Algebraic Classical Simulation beyond Free Fermions
New Pauli orbit and modified Gell-Mann bases enable polynomial-cost Lie-algebraic simulation for permutation-equivariant and bounded-excitation quantum dynamics.
-
Blind Symmetry Matching in Quantum States with Application to Shot-Count Reduction
A framework for blind discovery of finite-group symmetries in quantum states via scoring of candidate groups, with unbiased selection proven and a circuit that tests both weak commutation and strong charge-sector conf...
-
Exponentially many initializations to avoid barren plateaus
A first-moment operator diagnostic reveals exponentially many inequivalent initialization distributions avoid barren plateaus in variational quantum algorithms, with numerics indicating distinct attained minima.
-
Feature-level analysis and adversarial transfer in rotationally equivariant quantum machine learning
Rotationally equivariant quantum models can rely on vulnerable invariant statistics such as ring-averaged intensities, leaving them susceptible to classical transfer attacks, but suppressing the associated symmetry se...
-
The Lie Algebra of XY-mixer Topologies and Warm Starting QAOA for Constrained Optimization
The paper decomposes dynamical Lie algebras of XY-mixer topologies and demonstrates warm-starting QAOA via pre-training on restricted generators to improve convergence on constrained optimization problems.
-
Geometric Quantum Physics Informed Neural Network
GQPINNs add symmetry awareness to quantum PINNs via equivariant circuits, yielding lower mean absolute error and fewer parameters than standard QPINNs on linear and nonlinear PDE benchmarks.
-
Distributions of Noisy Expectation Values over Sets of Measurement Operators
Distributions of noisy expectation values over sets of measurement operators on random mixed states are derived combinatorially and approximated by fitted effective global-depolarizing models that match peaks in brick...
-
Fundamental limits to contrast reversal of survival probability correlations
Survival probability maps for any nontrivial pair of unitaries cannot achieve point-wise complementary correlation over the full projective state space, imposing a unitary-geometric limit on anti-contrast.
-
Resource-efficient equivariant quantum convolutional neural networks
Equivariant sp-QCNN encodes general symmetries with group theory, splits circuits at pooling layers to preserve symmetry while enabling parallel measurements, and shows improved efficiency and trainability over standa...
-
Quantum Convolutional Neural Networks are Effectively Classically Simulable
QCNNs are classically simulable via Pauli shadows on low-bodyness subspaces of locally-easy datasets, with explicit simulation demonstrated up to 1024 qubits for phases of matter classification.
-
Exploiting More Than Symmetry in Variational Quantum Machine Learning
Suitable subgroups preserve most generalization benefit in equivariant VQCs, but dominant gains come from placing trainable gates on task-decisive motifs rather than from varying symmetry level.
-
Beyond Logical Circuits: Hardware-Aware Analysis of Expressibility and Trainability in Variational Quantum Algorithms
Hardware transpilation of parameterized quantum circuits produces ansatz-dependent shifts in expressibility (up to 125%) and trainability (up to 25%), altering the expected trade-off between them.
-
A Review of Variational Quantum Algorithms: Insights into Fault-Tolerant Quantum Computing
A literature review of VQAs covering ansatz design, classical optimization, barren plateaus, error mitigation strategies, and theoretical adaptations for fault-tolerant quantum computing.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.