Signal detection in nearly continuous spectra and symmetry breaking

2020/11/30 by Vincent Lahoche, Dine Ousmane Samary, Mohamed Tamaazousti · 11 citations
Mathematics · Physics and Astronomy · #Artificial intelligence #Computer science #Covariance #Embedding #Formalism (music) #Gaussian #Mathematical physics #Mathematics #Physics #Quantum many-body systems #Quantum mechanics #Random Matrices and Applications #Renormalization #Renormalization group #Spectral line #Statistical physics #Statistics #Symmetry breaking #Theoretical and Computational Physics #hep-th

paper · pdf · open access · doi:10.3390/sym14030486

published in Symmetry 14(3), 486 (Multidisciplinary Digital Publishing Institute) · 07 pages, 6 figures

arxiv created 2021/05/28 · openalex publication_date 2022/02/28 · openalex created_date 2022/03/02 · arxiv updated 2022/03/04 · openalex updated_date 2026/07/22

Abstract

The large scale behavior of systems having a large number of interacting degrees of freedom is suitably described using renormalization group, from non-Gaussian distributions. Renormalization group techniques used in physics are then expected to be helpful for issues when standard methods in data analysis break down. 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 arXiv:2011.02376 to reproduces experimental correlations, we show in this paper that the presence of a signal may be characterized by a phase transition with ℤ₂-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.

Citations

• Field theoretical approach for signal detection in nearly continuous positive spectra I: Matricial data
• On the distribution of the largest eigenvalue in principal components analysis
• Exact evolution equation for the effective potential
• Information Theory and Statistical Mechanics
• The renormalization group: Critical phenomena and the Kondo problem
• Geometry of nonlinear least squares with applications to sloppy models and optimization
• DISTRIBUTION OF EIGENVALUES FOR SOME SETS OF RANDOM MATRICES
• Analysis of a complex of statistical variables into principal components.
• A survey of multilinear subspace learning for tensor data
• On the Distribution of the Roots of Certain Symmetric Matrices
• Scale-invariant feature extraction of neural network and renormalization group flow
• Machine learning and the physical sciences
• Information Theory and Statistical Mechanics. II