Strong replica symmetry for high-dimensional disordered log-concave Gibbs measures
arXiv:2009.12939 · doi:10.1093/imaiai/iaab027
Abstract
We consider a generic class of log-concave, possibly random, (Gibbs) measures. We prove the concentration of an infinite family of order parameters called multioverlaps. Because they completely parametrise the quenched Gibbs measure of the system, this implies a simple representation of the asymptotic Gibbs measures, as well as the decoupling of the variables in a strong sense. These results may prove themselves useful in several contexts. In particular in machine learning and high-dimensional inference, log-concave measures appear in convex empirical risk minimisation, maximum a-posteriori inference or M-estimation. We believe that they may be applicable in establishing some type of "replica symmetric formulas" for the free energy, inference or generalisation error in such settings.
References in corpus (37)
- Broken Replica Symmetry Bounds in the Mean Field Spin Glass Model
- The Thermodynamic Limit in Mean Field Spin Glass Models
- The generalization error of random features regression: Precise asymptotics and double descent curve
- A modern maximum-likelihood theory for high-dimensional logistic regression
- Optimal Errors and Phase Transitions in High-Dimensional Generalized Linear Models
- An Extended Variational Principle for the SK Spin-Glass Model
- General properties of overlap probability distributions in disordered spin systems. Toward Parisi ultrametricity
- On the Stability of the Quenched State in Mean Field Spin Glass Models
- Entropy and mutual information in models of deep neural networks
- Mutual information for symmetric rank-one matrix estimation: A proof of the replica formula
- Information-theoretic thresholds from the cavity method
- Spin glass models from the point of view of spin distributions
- The high temperature region of the Viana-Bray diluted spin glass model
- Statistical and computational phase transitions in spiked tensor estimation
- Mutual Information and Optimality of Approximate Message-Passing in Random Linear Estimation
- The adaptive interpolation method for proving replica formulas. Applications to the Curie-Weiss and Wigner spike models
- The Mutual Information in Random Linear Estimation Beyond i.i.d. Matrices
- Estimation in the spiked Wigner model: A short proof of the replica formula
- Charting the replica symmetric phase
- Absence of replica symmetry breaking in the random field Ising model
- Asymptotic Errors for Teacher-Student Convex Generalized Linear Models (or : How to Prove Kabashima's Replica Formula)
- Generalization error in high-dimensional perceptrons: Approaching Bayes error with convex optimization
- Counting good truth assignments of random k-SAT formulae
- A short proof of Paouris' inequality
- Harnessing the Bethe free energy
- A Precise Performance Analysis of Learning with Random Features
- Universality Laws for High-Dimensional Learning with Random Features
- The multi-species mean-field spin-glass on the Nishimori line
- Structure of finite-RSB asymptotic Gibbs measures in the diluted spin glass models
- Asymptotic errors for convex penalized linear regression beyond Gaussian matrices
- Fundamental Limits of Ridge-Regularized Empirical Risk Minimization in High Dimensions
- All-or-nothing statistical and computational phase transitions in sparse spiked matrix estimation
- 0-1 phase transitions in sparse spiked matrix estimation
- Compressed sensing with sparse, structured matrices
- Strong replica symmetry in high-dimensional optimal Bayesian inference
- Concentration of multi-overlaps for random ferromagnetic spin models
- Spin glass polynomial identities from entropic constraints