A spin glass model for reconstructing nonlinearly encrypted signals corrupted by noise
arXiv:1805.06982 · doi:10.1007/s10955-018-02217-9
Abstract
An encryption of a signal is a random mapping which can be corrupted by an additive noise. Given the Encryption Redundancy Parameter (ERP) , the signal strength parameter , and the ('bare') noise-to-signal ratio (NSR) , we consider the problem of reconstructing from its corrupted image by a Least Square Scheme for a certain class of random Gaussian mappings. The problem is equivalent to finding the configuration of minimal energy in a certain version of spherical spin glass model, with squared Gaussian-distributed random potential. We use the Parisi replica symmetry breaking scheme to evaluate the mean overlap between the original signal and its recovered image (known as 'estimator') as , which is a measure of the quality of the signal reconstruction. We explicitly analyze the general case of linear-quadratic family of random mappings and discuss the full curve. When nonlinearity exceeds a certain threshold but redundancy is not yet too big, the replica symmetric solution is necessarily broken in some interval of NSR. We show that encryptions with a nonvanishing linear component permit reconstructions with for any and any , with as . In contrast, for the case of purely quadratic nonlinearity, for any ERP there exists a threshold NSR value such that for making the reconstruction impossible. The behaviour close to the threshold is given by and is controlled by the replica symmetry breaking mechanism.
arXiv comment33 pages, 5 figures
References in corpus (13)
- Complexity of random smooth functions on the high-dimensional sphere
- Negative moments of characteristic polynomials of random matrices: Ingham-Siegel integral as an alternative to Hubbard-Stratonovich transformation
- Classical Particle in a Box with Random Potential: exploiting rotational symmetry of replicated Hamiltonian
- Topology trivialization and large deviations for the minimum in the simplest random optimization
- Fluctuations of the free energy of the spherical Sherrington-Kirkpatrick model
- Statistical mechanics of a single particle in a multiscale random potential: Parisi landscapes in finite dimensional Euclidean spaces
- Parisi formula, disorder chaos and fluctuation for the ground state energy in the spherical mixed p-spin models
- Renormalization Theory for Interacting Crumpled Manifolds
- Multifractality and Freezing Phenomena in Random Energy Landscapes: an Introduction
- Characteristic polynomials of random Hermitian matrices and Duistermaat-Heckman localisation on non-compact Kaehler manifolds
- On the dynamics of a spherical spin-glass
- Statics and dynamics of infinite-dimensional liquids and glasses: a parallel, compact derivation
- Phase diagram of matrix compressed sensing
Cited by in corpus (9)
- Nonlinearity-generated Resilience in Large Complex Systems
- Distribution of rare saddles in the -spin energy landscape
- A continuous constraint satisfaction problem for the rigidity transition in confluent tissues
- Analysis of overfitting in the regularized Cox model
- Finite size effects and loss of self-averageness in the relaxational dynamics of the spherical Sherrington-Kirkpatrick model
- Dynamical mean field theory for models of confluent tissues and beyond
- On the topology of solutions to random continuous constraint satisfaction problems
- Bilinear Sequence Regression: A Model for Learning from Long Sequences of High-dimensional Tokens
- Optimization landscape in the simplest constrained random least-square problem