Signal Detection in Nearly Continuous Spectra and ℤ$_{2}$-Symmetry Breaking
Résumé
The large scale behavior of systems having a large number of interacting degrees of freedom is suitably described using the renormalization group from non-Gaussian distributions. Renormalization group techniques used in physics are then expected to provide a complementary point of view on standard methods used in data science, especially for open issues. Signal detection and recognition for covariance matrices having nearly continuous spectra is currently an open issue in data science and machine learning. Using the field theoretical embedding introduced in Entropy, 23(9), 1132 to reproduce experimental correlations, we show in this paper that the presence of a signal may be characterized by a phase transition with -symmetry breaking. For our investigations, we use the nonperturbative renormalization group formalism, using a local potential approximation to construct an approximate solution of the flow. Moreover, we focus on the nearly continuous signal build as a perturbation of the Marchenko-Pastur law with many discrete spikes.
Mots clés
renormalization group
field theory
symmetry breaking
data analysis
signal detection
05.10.Cc
05.40.-a
07.05.Kf
Renormalization group
phase transition
big data
principal component analysis
renormalization group: nonperturbative
potential: approximation
potential: local
covariance
critical phenomena
non-Gaussianity
correlation
embedding
flow