$\beta$-Variational Autoencoder as an Entanglement Classifier

Abstract

We focus on using an architecture similar to the $\beta$-Variational Autoencoder ($\beta$-VAE) to discriminate if a quantum state is entangled or separable based on measurements. We split the data into two sets, the set of local and correlated measurements. Using the latent space, which is a low dimensional representation of the data, we show that restricting ourselves to the set of local data it is not possible to distinguish between entangled and separable states. Meanwhile, when considering both correlated and local measurements, an accuracy of over 80% is attained in the structure of the latent space.

arXiv comment5 pages, 4 figures

References in corpus (13)

• Adam: A Method for Stochastic Optimization
• Auto-Encoding Variational Bayes
• Quantum entanglement
• Separability Criterion for Density Matrices
• Separability of Mixed States: Necessary and Sufficient Conditions
• Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
• QuTiP 2: A Python framework for the dynamics of open quantum systems
• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• QuTiP: An open-source Python framework for the dynamics of open quantum systems
• Machine learning phases of matter
• Many-body quantum state tomography with neural networks
• Discovering physical concepts with neural networks
• Operationally meaningful representations of physical systems in neural networks

Cited by in corpus (2)

• From observations to complexity of quantum states via unsupervised learning
• Quantum variational learning for entanglement witnessing