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 (10)
- Broken Replica Symmetry Bounds in the Mean Field Spin Glass Model
- The high temperature region of the Viana-Bray diluted spin glass model
- Absence of replica symmetry breaking in the random field Ising model
- Counting good truth assignments of random k-SAT formulae
- A Precise Performance Analysis of Learning with Random Features
- Universality Laws for High-Dimensional Learning with Random Features
- Asymptotic errors for convex penalized linear regression beyond Gaussian matrices
- Fundamental Limits of Ridge-Regularized Empirical Risk Minimization in High Dimensions
- 0-1 phase transitions in sparse spiked matrix estimation
- Compressed sensing with sparse, structured matrices