Emergence of global receptive fields capturing multipartite quantum correlations
Oleg M. Sotnikov, Ilia A. Iakovlev, Evgeniy O. Kiktenko, Mikhail I. Katsnelson, Aleksey K. Fedorov, Vladimir V. Mazurenko

TL;DR
This paper demonstrates how neural network weight analysis reveals global structures in quantum states, enabling the creation of exact classical models for complex multipartite entanglement.
Contribution
It introduces a novel approach to interpret neural quantum states by monitoring weight space, leading to exact classical representations of Dicke states.
Findings
Identification of global convolutional structures in RBMs during quantum state learning
Development of an exact two-parameter classical model for Dicke states
Insights into neural network design for non-local quantum data
Abstract
In quantum physics, even simple data with a well-defined structure at the wave function level can be characterized by extremely complex correlations between its constituent elements. The inherent non-locality of the quantum correlations generally prevents one from providing their simple and transparent interpretation, which also remains a challenging problem for advanced classical techniques that approximate quantum states with neural networks. Here we show that monitoring the neural network weight space while learning quantum statistics from measurements allows to develop physical intuition about complex multipartite patterns and thus helps to construct more effective classical representations of the wave functions. Particularly, we observe the formation of distinct global convolutional structures, receptive fields in the hidden layer of the Restricted Boltzmann Machine (RBM) within…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
