A bound for the convergence rate of parallel tempering for sampling restricted Boltzmann machines

DOI10.1016/J.TCS.2015.05.019zbMath1329.68214OpenAlexW379579515MaRDI QIDQ496036

Asja Fischer, Christian Igel

Publication date: 16 September 2015

Published in: Theoretical Computer Science (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.tcs.2015.05.019

zbMATH Keywords

mixing timeparallel temperingrestricted Boltzmann machines

Mathematics Subject Classification ID

Computational methods in Markov chains (60J22) Learning and adaptive systems in artificial intelligence (68T05)

Related Items (1)

Algorithms for estimating the partition function of restricted Boltzmann machines

Uses Software

• darch

Cites Work

• Unnamed Item
• The flip-the-state transition operator for restricted Boltzmann machines
• Tuning tempered transitions
• Training restricted Boltzmann machines: an introduction
• Conditions for rapid mixing of parallel and simulated tempering on multimodal distributions
• Sufficient conditions for torpid mixing of parallel and simulated tempering
• What do we know about the Metropolis algorithm?
• Comparison theorems for reversible Markov chains
• Markov chain decomposition for convergence rate analysis
• Logarithmic Sobolev inequalities for finite Markov chains
• Bounding the Bias of Contrastive Divergence Learning
• Reducing the Dimensionality of Data with Neural Networks
• Training Products of Experts by Minimizing Contrastive Divergence
• Markov Chains
• On the swapping algorithm
• Justifying and Generalizing Contrastive Divergence

This page was built for publication: A bound for the convergence rate of parallel tempering for sampling restricted Boltzmann machines