Trainability and Expressivity of Hamming-Weight Preserving Quantum Circuits for Machine Learning

Abstract

Quantum machine learning (QML) has become a promising area for real world applications of quantum computers, but near-term methods and their scalability are still important research topics. In this context, we analyze the trainability and controllability of specific Hamming weight preserving variational quantum circuits (VQCs). These circuits use qubit gates that preserve subspaces of the Hilbert space, spanned by basis states with fixed Hamming weight $k$. In this work, we first design and prove the feasibility of new heuristic data loaders, performing quantum amplitude encoding of $\left(\genfrac{}{}{0ex}{}{n}{k}\right)$-dimensional vectors by training an $n$-qubit quantum circuit. These data loaders are obtained using controllability arguments, by checking the Quantum Fisher Information Matrix (QFIM)'s rank. Second, we provide a theoretical justification for the fact that the rank of the QFIM of any VQC state is almost-everywhere constant, which is of separate interest. Lastly, we analyze the trainability of Hamming weight preserving circuits, and show that the variance of the $l_2$ cost function gradient is bounded according to the dimension $\left(\genfrac{}{}{0ex}{}{n}{k}\right)$ of the subspace. This proves conditions of existence/lack of Barren Plateaus for these circuits, and highlights a setting where a recent conjecture on the link between controllability and trainability of variational quantum circuits does not apply.

References in corpus (25)

• Quantum algorithm for solving linear systems of equations
• Variational Quantum Algorithms
• Barren plateaus in quantum neural network training landscapes
• Quantum principal component analysis
• Cost Function Dependent Barren Plateaus in Shallow Parametrized Quantum Circuits
• From the Quantum Approximate Optimization Algorithm to a Quantum Alternating Operator Ansatz
• The effect of data encoding on the expressive power of variational quantum machine learning models
• Quantum Fisher information matrix and multiparameter estimation
• Towards Practical Quantum Variational Algorithms
• Connecting ansatz expressibility to gradient magnitudes and barren plateaus
• Complete controllability of quantum systems
• Beyond Barren Plateaus: Quantum Variational Algorithms Are Swamped With Traps
• Diagnosing Barren Plateaus with Tools from Quantum Optimal Control
• Matchgates and classical simulation of quantum circuits
• Exploiting symmetry in variational quantum machine learning
• Group-Invariant Quantum Machine Learning
• A Lie Algebraic Theory of Barren Plateaus for Deep Parameterized Quantum Circuits
• Classical and Quantum Fisher Information in the Geometrical Formulation of Quantum Mechanics
• Quantum Methods for Neural Networks and Application to Medical Image Classification
• Quantum Vision Transformers
• Symbolic integration with respect to the Haar measure on the unitary group
• Quantum Spectral Clustering
• The Adjoint Is All You Need: Characterizing Barren Plateaus in Quantum Ansätze
• Efficient classical algorithms for simulating symmetric quantum systems
• Subspace Preserving Quantum Convolutional Neural Network Architectures

Cited by in corpus (6)

• Does provable absence of barren plateaus imply classical simulability?
• Quantum Convolutional Neural Networks are Effectively Classically Simulable
• Constrained and Vanishing Expressivity of Quantum Fourier Models
• Architectures and random properties of symplectic quantum circuits
• Quantum feature-map learning with reduced resource overhead
• Double-bracket quantum algorithms for high-fidelity ground state preparation