Learning the Einstein-Podolsky-Rosen correlations on a Restricted Boltzmann Machine
Steven Weinstein

TL;DR
This paper presents a Restricted Boltzmann Machine model that reproduces EPR correlations, violating Bell's inequality by sacrificing measurement independence rather than locality, offering a novel hidden-variable perspective.
Contribution
It introduces a hidden-variable model using a Restricted Boltzmann Machine that reproduces quantum correlations without violating locality.
Findings
Model reproduces EPR correlations
Violates Bell inequality via measurement independence
Maintains locality in the hidden-variable model
Abstract
We construct a hidden variable model for the EPR correlations using a Restricted Boltzmann Machine. The model reproduces the expected correlations and thus violates the Bell inequality, as required by Bell's theorem. Unlike most hidden-variable models, this model does not violate the assumption in Bell's argument. Rather, it violates , albeit in a decidedly non-conspiratorial way.
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.
Taxonomy
TopicsQuantum Computing Algorithms and Architecture · Opinion Dynamics and Social Influence · Quantum many-body systems
