Skip to main content
Search

# Mean-field approximation

2 related articles

Subscribe to updates
  1. arXiv

    Likelihood tempering in linear Bayesian neural networks makes predictive mean and variance transition at different temperature scales, so no schedule recovers both NNGP posterior moments

    For single-hidden-layer linear Bayesian neural networks under NTK parameterization, the authors derive the limiting variational predictive distribution when the temperature decays as a power of width, and find that the predictive mean and variance undergo phase transitions at different temperature scales: the mean leaves its prior value below an explicit threshold and eventually equals the least-squares prediction, while the variance departs from the prior only at colder temperatures, and no schedule of this form recovers both the untempered NNGP posterior mean and variance.

  2. Bhattacharya, Deb and Mukherjee write the free-energy limit of multilinear Gibbs measures as an infinite-dimensional optimization, with sufficient conditions and counterexamples for replica symmetry

    The paper studies multilinear Gibbs measures whose Hamiltonian is a generalized U-statistic with a general base measure; under cut-norm convergence of the coupling matrices it expresses the limiting free energy as an infinite-dimensional optimization over functions, gives sufficient conditions for replica symmetry (constant optimizers) and uses counterexamples to show their necessity, and derives weak limits for local fields, the Hamiltonian and global magnetization, a universal weak law for contrasts n-1Σc_iX_i→0 when Σc_i=o(n), exponential concentration bounds for local and global magnetizations, and existence of a sharp phase transition in the temperature parameter for higher-order interactions.

You’re all caught up