Infinite Swapping Algorithm for Training Restricted Boltzmann Machines

DOI10.1007/978-3-030-43465-6_14MaRDI QIDQ5117935zbMATH OpenOpenAlexFDO

Authors Henrik Hult, Pierre Nyquist, Carl Ringqvist

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

latent variable modelsstatistical learningGibbs samplingrestricted Boltzmann machinesinfinite swapping

Mathematics Subject Classification ID

Monte Carlo methods (65C05)

Cites work

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

Cited in

(2)

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

This page was built for publication: Infinite Swapping Algorithm for Training Restricted Boltzmann Machines

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5117935)