Entangled Datasets for Quantum Machine Learning

Abstract

High-quality, large-scale datasets have played a crucial role in the development and success of classical machine learning. Quantum Machine Learning (QML) is a new field that aims to use quantum computers for data analysis, with the hope of obtaining a quantum advantage of some sort. While most proposed QML architectures are benchmarked using classical datasets, there is still doubt whether QML on classical datasets will achieve such an advantage. In this work, we argue that one should instead employ quantum datasets composed of quantum states. For this purpose, we introduce the NTangled dataset composed of quantum states with different amounts and types of multipartite entanglement. We first show how a quantum neural network can be trained to generate the states in the NTangled dataset. Then, we use the NTangled dataset to benchmark QML models for supervised learning classification tasks. We also consider an alternative entanglement-based dataset, which is scalable and is composed of states prepared by quantum circuits with different depths. As a byproduct of our results, we introduce a novel method for generating multipartite entangled states, providing a use-case of quantum neural networks for quantum entanglement theory.

arXiv comment12 + 8 pages, 10 + 3 figures, 1 table

References in corpus (48)

• Quantum entanglement
• Quantum Computing in the NISQ era and beyond
• Quantum Machine Learning
• A variational eigenvalue solver on a quantum processor
• Three qubits can be entangled in two inequivalent ways
• Hardware-efficient Variational Quantum Eigensolver for Small Molecules and Quantum Magnets
• Probing many-body dynamics on a 51-atom quantum simulator
• QuTiP 2: A Python framework for the dynamics of open quantum systems
• Barren plateaus in quantum neural network training landscapes
• Quantum machine learning in feature Hilbert spaces
• Quantum Convolutional Neural Networks
• Cost Function Dependent Barren Plateaus in Shallow Parametrized Quantum Circuits
• Circuit-centric quantum classifiers
• The power of quantum neural networks
• Noise-Induced Barren Plateaus in Variational Quantum Algorithms
• The effect of data encoding on the expressive power of variational quantum machine learning models
• Efficient Learning for Deep Quantum Neural Networks
• Connecting ansatz expressibility to gradient magnitudes and barren plateaus
• Optimal Quantum Circuits for General Two-Qubit Gates
• A generative modeling approach for benchmarking and training shallow quantum circuits
• Absence of Barren Plateaus in Quantum Convolutional Neural Networks
• Robust data encodings for quantum classifiers
• A potential multipartide entanglement measure
• An Artificial Neuron Implemented on an Actual Quantum Processor
• Information-theoretic bounds on quantum advantage in machine learning
• The Schmidt Measure as a Tool for Quantifying Multi-Particle Entanglement
• PennyLane: Automatic differentiation of hybrid quantum-classical computations
• Diagnosing Barren Plateaus with Tools from Quantum Optimal Control
• Training of Quantum Circuits on a Hybrid Quantum Computer
• Equivalence of quantum barren plateaus to cost concentration and narrow gorges
• Quantum principal component analysis only achieves an exponential speedup because of its state preparation assumptions
• Barren plateaus preclude learning scramblers
• Higher Order Derivatives of Quantum Neural Networks with Barren Plateaus
• Approximate unitary $t$-designs by short random quantum circuits using nearest-neighbor and long-range gates
• Multipartite entanglement measures
• Tripartite entanglement transformations and tensor rank
• Computable and operationally meaningful multipartite entanglement measures
• Quantum embeddings for machine learning
• Machine Learning Phase Transitions with a Quantum Processor
• Reformulation of the No-Free-Lunch Theorem for Entangled Data Sets
• Unification of different views of decoherence and discord
• Entanglement spectroscopy with a depth-two quantum circuit
• Strong bound between trace distance and Hilbert-Schmidt distance for low-rank states
• Multipartite monogamy of the concurrence
• A Quantum Model for Autonomous Learning Automata
• One-body entanglement as a quantum resource in fermionic systems
• The Inductive Bias of Quantum Kernels
• A Unified Framework for Quantum Supervised Learning

Cited by in corpus (8)

• Challenges and Opportunities in Quantum Machine Learning
• Generalization in quantum machine learning from few training data
• Theory of overparametrization in quantum neural networks
• ResQNets: A Residual Approach for Mitigating Barren Plateaus in Quantum Neural Networks
• Transition Role of Entangled Data in Quantum Machine Learning
• GSQAS: Graph Self-supervised Quantum Architecture Search
• Quantum variational learning for entanglement witnessing
• Quantum continual learning of quantum data realizing knowledge backward transfer