Pith. sign in

REVIEW

Learning disentangled representation for classical models

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2110.08082 v2 pith:KHI3H5NE submitted 2021-10-15 cond-mat.str-el cond-mat.stat-mech

classification cond-mat.str-elcond-mat.stat-mech
keywords disentangledbetaclassicallearningmodelsrepresentationdecoderdeep
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
abstract

Finding disentangled representation plays a predominant role in the success of modern deep learning applications, but the results lack a straightforward explanation. Here we apply the information bottleneck method and its $\beta$-VAE implementation to find the disentangled low-dimensional representation of classical models. For the Ising model, our results reveal a deep connection between the disentangled features and the physical order parameters, and the widely-used Bernoulli decoder is found to be learning a mean-field Hamiltonian at fixed temperature. This analogy motivates us to extend the application of $\beta$-VAE to more complex classical models with non-binary variables using different decoder neural network and propose a modified architecture $\beta^2$-VAE to enforce thermal fluctuations in generated samples. Our work provides a way to design novel physics-informed algorithm that can yield learned features in potential correspondence with real physical properties.

Discussion (0). Continue with ORCID to comment.

Pith tools