Infinite Swapping Algorithm for Training Restricted Boltzmann Machines

DOI10.1007/978-3-030-43465-6_14OpenAlexW3023497326MaRDI QIDQ5117935

Pierre Nyquist, Carl Ringqvist, Henrik Hult

Publication date: 26 August 2020

Published in: Springer Proceedings in Mathematics & Statistics (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/978-3-030-43465-6_14

zbMATH Keywords

Gibbs samplingrestricted Boltzmann machineslatent variable modelsstatistical learninginfinite swapping

Mathematics Subject Classification ID

Monte Carlo methods (65C05)

Related Items

Spectral gap of replica exchange Langevin diffusion on mixture distributions ⋮ Ergodicity of the infinite swapping algorithm at low temperature

Cites Work

• A large deviations analysis of certain qualitative properties of parallel tempering and infinite swapping algorithms
• Monte Carlo strategies in scientific computing.
• Training Products of Experts by Minimizing Contrastive Divergence
• 3D spin glass and 2D ferromagneticXYmodel: a comparison
• Annealing Markov Chain Monte Carlo with Applications to Ancestral Inference
• On the Infinite Swapping Limit for Parallel Tempering