Functional renormalization group for signal detection and stochastic ergodicity breaking

Abstract

Signal detection is one of the main challenges of data science. As it often happens in data analysis, the signal in the data may be corrupted by noise. There is a wide range of techniques aimed at extracting the relevant degrees of freedom from data. However, some problems remain difficult. It is notably the case of signal detection in almost continuous spectra when the signal-to-noise ratio is small enough. This paper follows a recent bibliographic line which tackles this issue with field-theoretical methods. Previous analysis focused on equilibrium Boltzmann distributions for some effective field representing the degrees of freedom of data. It was possible to establish a relation between signal detection and ${\mathbb{Z}}_2$-symmetry breaking. In this paper, we consider a stochastic field framework inspiring by the so-called "Model A", and show that the ability to reach or not an equilibrium state is correlated with the shape of the dataset. In particular, studying the renormalization group of the model, we show that the weak ergodicity prescription is always broken for signals small enough, when the data distribution is close to the Marchenko-Pastur (MP) law. This, in particular, enables the definition of a detection threshold in the regime where the signal-to-noise ratio is small enough.

arXiv comment28 pages, 11 figures

References in corpus (31)

• Exact evolution equation for the effective potential
• The Exact Renormalisation Group and Approximate Solutions
• Optimised Renormalisation Group Flows
• The nonperturbative functional renormalization group and its applications
• An Introduction to the Nonperturbative Renormalization Group
• Derivative Expansion of the Exact Renormalization Group
• Von Neumann Algebra Automorphisms and Time-Thermodynamics Relation in General Covariant Quantum Theories
• Mutual Information, Neural Networks and the Renormalization Group
• Coarse--graining, fixed points, and scaling in a large population of neurons
• Neural Network Renormalization Group
• Symmetries of generating functionals of Langevin processes with colored multiplicative noise
• General framework of the non-perturbative renormalization group for non-equilibrium steady states
• PCA meets RG
• Neural Networks and Quantum Field Theory
• Frequency regulators for the nonperturbative renormalization group: A general study and the model A as a benchmark
• Nonperturbative renormalization for the neural network-QFT correspondence
• Is Deep Learning a Renormalization Group Flow?
• The renormalisation group via statistical inference
• Renormalization Group Flow as Optimal Transport
• Field theoretical approach for signal detection in nearly continuous positive spectra II: Tensorial data
• Functional renormalization group for multilinear disordered Langevin dynamics I: Formalism and first numerical investigations at equilibrium
• Signal detection in nearly continuous spectra and symmetry breaking
• Functional renormalization group for multilinear disordered Langevin dynamics II: Revisiting the $p=2$ spin dynamics for Wigner and Wishart ensembles
• Field theoretical approach for signal detection in nearly continuous positive spectra I: Matricial data
• Symmetry-via-Duality: Invariant Neural Network Densities from Parameter-Space Correlators
• Resummed mean-field inference for strongly coupled data
• Inferring relevant features: from QFT to PCA
• Why Unsupervised Deep Networks Generalize
• Short sighted deep learning
• Renormalization in the neural network-quantum field theory correspondence
• Multi-Relevance: Coexisting but Distinct Notions of Scale in Large Systems

Cited by in corpus (2)

• 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