Replica calculations fully solve spherical Boltzmann machine ensembles and identify regimes where ensemble learning outperforms standard training, particularly for nearly finite-dimensional data.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cond-mat.dis-nn 2years
2026 2representative citing papers
Frequency dispersion in a random-interaction spherical oscillator model suppresses finite-temperature spin-glass ordering because the resulting correlation singularity violates the spherical constraint, but zero-temperature glassiness persists.
citing papers explorer
-
Replica Theory of Spherical Boltzmann Machine Ensembles
Replica calculations fully solve spherical Boltzmann machine ensembles and identify regimes where ensemble learning outperforms standard training, particularly for nearly finite-dimensional data.
-
A solvable model of noisy coupled oscillators with fully random interactions
Frequency dispersion in a random-interaction spherical oscillator model suppresses finite-temperature spin-glass ordering because the resulting correlation singularity violates the spherical constraint, but zero-temperature glassiness persists.