Abstract
Restricted Boltzmann Machines (RBM’s) are unsupervised probabilistic neural networks that can be stacked to form Deep Belief Networks. Given the recent popularity of RBM’s and the increasing availability of parallel computing architectures, it becomes interesting to investigate learning algorithms for RBM’s that benefit from parallel computations. In this paper, we look at two extensions of the parallel tempering algorithm, which is a Markov Chain Monte Carlo method to approximate the likelihood gradient. The first extension is directed at a more effective exchange of information among the parallel sampling chains. The second extension estimates gradients by averaging over chains from different temperatures. We investigate the efficiency of the proposed methods and demonstrate their usefulness on the MNIST dataset. Especially the weighted averaging seems to benefit Maximum Likelihood learning.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Athènes, M., Calvo, F.: Multiple-Replica Exchange with Information Retrieval. Chemphyschem. 9(16), 2332–2339 (2008)
Bengio, Y.: Learning deep architectures for AI. Foundations and Trends in Machine Learning 2(1), 1–127 (2009), also published as a book. Now Publishers (2009)
Brenner, P., Sweet, C.R., VonHandorf, D., Izaguirre, J.A.: Accelerating the Replica Exchange Method through an Efficient All-Pairs Exchange. The Journal of Chemical Physics 126(7), 074103 (2007)
Desjardins, G., Courville, A.C., Bengio, Y., Vincent, P., Delalleau, O.: Tempered markov chain monte carlo for training of restricted boltzmann machines. Journal of Machine Learning Research - Proceedings Track 9, 145–152 (2010)
Freund, Y., Haussler, D.: Unsupervised Learning of Distributions on Binary Vectors Using Two Layer Networks. Tech. rep., Santa Cruz, CA, USA (1994)
Hinton, G.E.: Training Products of Experts by Minimizing Contrastive Divergence. Neural Computation 14(8), 1771–1800 (2002)
Hinton, G.E., Osindero, S., Teh, Y.W.: A fast learning algorithm for deep belief nets. Neural Computation 18(7), 1527–1554 (2006)
Neal, R.M.: Annealed importance sampling. Statistics and Computing 11, 125–139 (1998)
Salakhutdinov, R.: Learning in markov random fields using tempered transitions. In: Bengio, Y., Schuurmans, D., Lafferty, J.D., Williams, C.K.I., Culotta, A. (eds.) NIPS, pp. 1598–1606. Curran Associates, Inc. (2009)
Salakhutdinov, R., Murray, I.: On the quantitative analysis of Deep Belief Networks. In: McCallum, A., Roweis, S. (eds.) Proceedings of the 25th Annual International Conference on Machine Learning (ICML 2008), pp. 872–879. Omnipress (2008)
Swendsen, R.H., Wang, J.S.: Replica Monte Carlo Simulation of Spin-Glasses. Physical Review Letters 57(21), 2607–2609 (1986)
Tieleman, T., Hinton, G.: Using Fast Weights to Improve Persistent Contrastive Divergence. In: Proceedings of the 26th International Conference on Machine Learning, pp. 1033–1040. ACM, New York (2009)
Tieleman, T.: Training restricted Boltzmann machines using approximations to the likelihood gradient. In: Proceedings of the International Conference on Machine Learning (2008)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Brakel, P., Dieleman, S., Schrauwen, B. (2012). Training Restricted Boltzmann Machines with Multi-tempering: Harnessing Parallelization. In: Villa, A.E.P., Duch, W., Érdi, P., Masulli, F., Palm, G. (eds) Artificial Neural Networks and Machine Learning – ICANN 2012. ICANN 2012. Lecture Notes in Computer Science, vol 7553. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-33266-1_12
Download citation
DOI: https://doi.org/10.1007/978-3-642-33266-1_12
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-33265-4
Online ISBN: 978-3-642-33266-1
eBook Packages: Computer ScienceComputer Science (R0)