Signal detection in nearly continuous spectra and symmetry breaking

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 ${\mathbb{Z}}_2$-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.

arXiv comment07 pages, 6 figures

References in corpus (39)

• Machine learning and the physical sciences
• Exact evolution equation for the effective potential
• Non-Perturbative Renormalization Flow in Quantum Field Theory and Statistical Physics
• Noise Dressing of Financial Correlation Matrices
• Optimisation of the exact renormalisation group
• An Introduction to the Nonperturbative Renormalization Group
• Parameter Space Compression Underlies Emergent Theories and Predictive Models
• Searching for collective behavior in a network of real neurons
• The geometry of nonlinear least squares with applications to sloppy models and optimization
• Mutual Information, Neural Networks and the Renormalization Group
• The sloppy model universality class and the Vandermonde matrix
• Collective behavior of place and non-place neurons in the hippocampal network
• Neural Network Renormalization Group
• Coarse--graining, fixed points, and scaling in a large population of neurons
• Lectures on renormalization and asymptotic safety
• Derivative expansion and renormalisation group flows
• PCA meets RG
• Non perturbative renormalisation group and momentum dependence of $n$-point functions (I)
• Optimality and Sub-optimality of PCA I: Spiked Random Matrix Models
• Scale-invariant Feature Extraction of Neural Network and Renormalization Group Flow
• Neural Networks and Quantum Field Theory
• Non perturbative renormalization group and momentum dependence of n-point functions (II)
• Information geometric approach to the renormalisation group
• Nonperturbative renormalization for the neural network-QFT correspondence
• Is Deep Learning a Renormalization Group Flow?
• Universal entanglement of typical states in constrained systems
• Quantifying randomness in protein-protein interaction networks of different species: A random matrix approach
• Renormalization Group Improvement of the Effective Potential: an EFT Approach
• Time series, correlation matrices and random matrix models
• Revisited functional renormalization group approach for random matrices in the large-$N$ limit
• Field theoretical approach for signal detection in nearly continuous positive spectra II: Tensorial data
• Neural Monte Carlo Renormalization Group
• Reliability of the local truncations for the random tensor models renormalization group flow
• Adding machine learning within Hamiltonians: Renormalization group transformations, symmetry breaking and restoration
• Spectral renormalization group theory on networks
• Field theoretical approach for signal detection in nearly continuous positive spectra I: Matricial data
• Inferring relevant features: from QFT to PCA
• Coarse-grained distinguishability of field interactions
• Generalized scale behavior and renormalization group for data analysis

Cited by in corpus (8)

• Functional renormalization group for multilinear disordered Langevin dynamics I: Formalism and first numerical investigations at equilibrium
• Functional renormalization group for multilinear disordered Langevin dynamics II: Revisiting the $p=2$ spin dynamics for Wigner and Wishart ensembles
• Functional renormalization group for signal detection and stochastic ergodicity breaking
• Functional renormalization group for p=2 like glassy matrices in the planar approximation: I. Vertex expansion at equilibrium
• An intriguing connection between Pisarski's fixed point and (2+3)-spin glasses
• Functional Renormalization Group Approach for Signal Detection
• Functional Renormalization for Signal Detection: Dimensional Analysis and Dimensional Phase Transition for Nearly Continuous Spectra Effective Field Theory
• Signal inference in financial stock return correlations through phase-ordering kinetics in the quenched regime