pith. sign in

arxiv: 2110.08082 · v2 · pith:KHI3H5NEnew · submitted 2021-10-15 · ❄️ cond-mat.str-el · cond-mat.stat-mech

Learning disentangled representation for classical models

classification ❄️ cond-mat.str-el cond-mat.stat-mech
keywords disentangledbetaclassicallearningmodelsrepresentationdecoderdeep
0
0 comments X
read the original 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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.