Examples of renormalization group transformations for image sets
arXiv:1807.10250 · doi:10.1103/PhysRevE.98.052129
Abstract
Using the example of configurations generated with the worm algorithm for the two-dimensional Ising model, we propose renormalization group (RG) transformations, inspired by the tensor RG, that can be applied to sets of images. We relate criticality to the logarithmic divergence of the largest principal component. We discuss the changes in link occupation under the RG transformation, suggest ways to obtain data collapse, and compare with the two state tensor RG approximation near the fixed point.
References in corpus (17)
- Machine learning phases of matter
- Tensor renormalization group approach to 2D classical lattice models
- Discovering Phase Transitions with Unsupervised Learning
- Unsupervised learning of phase transitions: from principal component analysis to variational autoencoders
- Coarse-graining renormalization by higher-order singular value decomposition
- Worm algorithms for classical statistical models
- Discovering Phases, Phase Transitions and Crossovers through Unsupervised Machine Learning: A critical examination
- Second Renormalization of Tensor-Network States
- Exact blocking formulas for spin and gauge models
- Tensor renormalization group study of classical XY model on the square lattice
- PCA meets RG
- Reconstruction of signals with unknown spectra in information field theory with parameter uncertainty
- Machine learning action parameters in lattice quantum chromodynamics
- Controlling sign problems in spin models using tensor renormalization
- Accurate exponents from approximate tensor renormalizations
- RG inspired Machine Learning for lattice field theory
- Tensor-product representations for string-net condensed states
Cited by in corpus (6)
- The critical temperature of the 2D-Ising model through Deep Learning Autoencoders
- Automatic Differentiation for Second Renormalization of Tensor Networks
- Beauty and structural complexity
- Discrete aspects of continuous symmetries in the tensorial formulation of Abelian gauge theories
- Deep learning of phase transitions with minimal examples
- Logical Reasoning for Revealing the Critical Temperature through Deep Learning of Configuration Ensemble of Statistical Systems