Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

Unsupervised Machine Learning of the Contact Process

F. W. S. Lima, L. Brito, Gladstone Alencar Alves, A. Macedo-Filho, Ronan Silva Ferreira, T. F. A. Alves

Published Jan 1, 2026• 0 citations
Publisher
DOI
10.2139/ssrn.7484527

Related papers

Unsupervised machine learning quantum dynamics

Matthew Choi, Daniel Flam-Shepherd, Thi Ha Kyaw +1 more

Bulletin of the American Physical Society•Mar 19, 2021•0 citations

Identifying topological order through unsupervised machine learning

Joaquin F. Rodriguez-Nieva, Mathias S. Scheurer

arXiv:1805.05961•Nature Physics•May 6, 2019•296 citations

Unsupervised machine learning of phase transition in percolation

Wei Yu, Pin Lyu

Physica A Statistical Mechanics and its Applications•Aug 14, 2020•19 citations

Unsupervised machine learning of topological phase transitions

Joaquin F. Rodriguez-Nieva, Mathias S. Scheurer

Bulletin of the American Physical Society•Mar 4, 2020•0 citations

Unsupervised machine learning approaches to the q-state Potts model

Andrea Tirelli, Danyella O. Carvalho, Lucas A. Oliveira +3 more

arXiv:2112.06735•The European Physical Journal B•Nov 1, 2022•18 citations

Unsupervised Machine Learning of the Contact Process

L. T. Brito, Gladstone Alencar Alves, F. W. S. Lima +3 more

We investigate how unsupervised machine-learning methods can characterize the active-absorbing phase transition in the contact process in one and two spatial dimensions. Our analysis focuses on principal component analysis (PCA) and variational autoencoders (VAEs), and we show that direct applications of these methods encounter a central difficulty: contact process configurations are intrinsically positive-definite. In the PCA case, standard centering procedures fail to isolate the order parameter in the leading component. To address this, we augment the data with sign-reversed configurations, creating a balanced dataset with zero mean while preserving the density information required to describe the transition. This preprocessing allows the dominant principal component to recover the order parameter and reproduce the expected finite-size scaling near criticality. For VAEs, we find a related limitation: a fixed Gaussian prior does not provide sufficient latent regularization across the full range of control parameters and system sizes for positive-definite data. We overcome this by adopting a heteroscedastic Gaussian prior that adapts to the control parameter, leading to a substantial improvement in the finite-size scaling of reconstruction-based observables near the critical threshold. Taken together, these results highlight a key lesson: the success of machine learning in phase-transition problems does not rely on algorithmic complexity alone, but on tailoring the representation to respect the physical structure of the system, including its intrinsic constraints and symmetries.

arXiv:2609.16506•Sep 15, 2026•0 citations
We investigate how unsupervised machine-learning methods can characterize the active-absorbing phase transition in the contact process in one and two spatial dimensions. Our analysis focuses on principal component analysis (PCA) and variational autoencoders (VAEs), and we show that direct applications of these methods encounter a central difficulty: contact process configurations are intrinsically positive-definite. In the PCA case, standard centering procedures fail to isolate the order parameter in the leading component. To address this, we augment the data with sign-reversed configurations, creating a balanced dataset with zero mean while preserving the density information required to describe the transition. This preprocessing allows the dominant principal component to recover the order parameter and reproduce the expected finite-size scaling near criticality. For VAEs, we find a related limitation: a fixed Gaussian prior does not provide sufficient latent regularization across the full range of control parameters and system sizes for positive-definite data. We overcome this by adopting a heteroscedastic Gaussian prior that adapts to the control parameter, leading to a substantial improvement in the finite-size scaling of reconstruction-based observables near the critical threshold. Taken together, these results highlight a key lesson: the success of machine learning in phase-transition problems does not rely on algorithmic complexity alone, but on tailoring the representation to respect the physical structure of the system, including its intrinsic constraints and symmetries.