Learning complexity gradually in quantum machine learning models

Abstract

Quantum machine learning is an emergent field that continues to draw significant interest for its potential to offer improvements over classical algorithms in certain areas. However, training quantum models remains a challenging task, largely because of the difficulty in establishing an effective inductive bias when solving high-dimensional problems. In this work, we propose a training framework that prioritizes informative data points over the entire training set. This approach draws inspiration from classical techniques such as curriculum learning and hard example mining to introduce an additional inductive bias through the training data itself. By selectively focusing on informative samples, we aim to steer the optimization process toward more favorable regions of the parameter space. This data-centric approach complements existing strategies such as warm-start initialization methods, providing an additional pathway to address performance challenges in quantum machine learning. We provide theoretical insights into the benefits of prioritizing informative data for quantum models, and we validate our methodology with numerical experiments on selected recognition tasks of quantum phases of matter. Our findings indicate that this strategy could be a valuable approach for improving the performance of quantum machine learning models.

12 + 4 pages, 9 figures, 5 tables

References in corpus (47)

• Barren plateaus in quantum neural network training landscapes
• Quantum Convolutional Neural Networks
• Machine learning phases of matter
• Evaluating analytic gradients on quantum hardware
• Classifying quantum phases using Matrix Product States and PEPS
• The effect of data encoding on the expressive power of variational quantum machine learning models
• Efficient Learning for Deep Quantum Neural Networks
• Challenges and Opportunities in Quantum Machine Learning
• Data re-uploading for a universal quantum classifier
• A rigorous and robust quantum speed-up in supervised machine learning
• Generalization in quantum machine learning from few training data
• Evenly distributed unitaries: on the structure of unitary designs
• Information-theoretic bounds on quantum advantage in machine learning
• Learning the quantum algorithm for state overlap
• Beyond Barren Plateaus: Quantum Variational Algorithms Are Swamped With Traps
• Diagnosing Barren Plateaus with Tools from Quantum Optimal Control
• One-Dimensional Symmetry Protected Topological Phases and their Transitions
• Barren Plateaus in Variational Quantum Computing
• Exploiting symmetry in variational quantum machine learning
• Group-Invariant Quantum Machine Learning
• A Lie Algebraic Theory of Barren Plateaus for Deep Parameterized Quantum Circuits
• TensorCircuit: a Quantum Software Framework for the NISQ Era
• Machine learning of noise-resilient quantum circuits
• Many-body topological invariants from randomized measurements
• Theoretical Guarantees for Permutation-Equivariant Quantum Neural Networks
• ADAPT-VQE is insensitive to rough parameter landscapes and barren plateaus
• On the Quantum versus Classical Learnability of Discrete Distributions
• Understanding quantum machine learning also requires rethinking generalization
• Hamiltonian variational ansatz without barren plateaus
• Shadows of quantum machine learning
• Avoiding barren plateaus via transferability of smooth solutions in Hamiltonian Variational Ansatz
• Synergy Between Quantum Circuits and Tensor Networks: Short-cutting the Race to Practical Quantum Advantage
• Quantum Phase Recognition via Quantum Kernel Methods
• Model-Independent Learning of Quantum Phases of Matter with Quantum Convolutional Neural Networks
• Quantum Error Correction with Quantum Autoencoders
• Trainability Enhancement of Parameterized Quantum Circuits via Reduced-Domain Parameter Initialization
• Variational quantum simulation: a case study for understanding warm starts
• Lie-algebraic classical simulations for quantum computing
• Optimal quantum dataset for learning a unitary transformation
• A super-polynomial quantum-classical separation for density modelling
• What can we learn from quantum convolutional neural networks?
• Neural quantum kernels: training quantum kernels with quantum neural networks
• Noise-induced shallow circuits and absence of barren plateaus
• Barren plateaus are swamped with traps
• Error-tolerant quantum convolutional neural networks for symmetry-protected topological phases
• Backpropagation scaling in parameterised quantum circuits
• Quantum Curriculum Learning