Quickly Generating Representative Samples from an RBM-Derived Process
The DOI matches its Crossref record; 2 of the 2 references it cites were found in a registry or an index.
Abstract
Two recently proposed learning algorithms, herding and fast persistent contrastive divergence (FPCD), share the following interesting characteristic: they exploit changes in the model parameters while sampling in order to escape modes and mix better during the sampling process that is part of the learning algorithm. We justify such approaches as ways to escape modes while keeping approximately the same asymptotic distribution of the Markov chain. In that spirit, we extend FPCD using an idea borrowed from Herding in order to obtain a pure sampling algorithm, which we call the rates-FPCD sampler. Interestingly, this sampler can improve the model as we collect more samples, since it optimizes a lower bound on the log likelihood of the training data. We provide empirical evidence that this new algorithm displays substantially better and more robust mixing than Gibbs sampling.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Training Products of Experts by Minimizing Contrastive Divergence
Hinton, G. E. (2002) · Neural Computation · doi:10.1162/089976602760128018 · Cited by 4,879 · cited 1×
“The CD training algorithm (Hinton, 1999, 2002; Hinton et al., 2006) obtains these samples by iterating one or more steps of a block Gibbs chain initialized on an observed example x .”
MethodUsing fast weights to improve persistent contrastive divergence
Tieleman, T., & Hinton, G. (2009) · Proceedings of the 26th Annual International Conference on Machine Learning · doi:10.1145/1553374.1553506 · Cited by 274 · cited 3×
“More recent work has gone even further: the fast persistent contrastive divergence (FPCD) algorithm (Tieleman & Hinton, 2009) keeps a second set of parameters (updated with a stronger gradient but decayed to zero) that are added to the true parameters only for sampling part of the learning…”
BackgroundMethodInfluential
Cited by
GAN(Generative Adversarial Nets)
(2017) · Journal of Japan Society for Fuzzy Theory and Intelligent Informatics · doi:10.3156/jsoft.29.5_177_2 · Cited by 19,270
Representation Learning: A Review and New Perspectives
Bengio, Y., Courville, A., & Vincent, P. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2013.50 · Cited by 13,001
Self-citationGenerative Adversarial Networks
(2022) · The Science of Deep Learning · doi:10.1017/9781108891530.013 · Cited by 2,402
Practical Recommendations for Gradient-Based Training of Deep Architectures
Bengio, Y. (2012) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-35289-8_26 · Cited by 2,259
“An interesting alternative is rates-FPCD (Tieleman and Hinton, 2009; Breuleux et al. , 2011) which appears to be more robust to this problem and generally mixes faster, but at the cost of losing theoretical guarantees.”
BackgroundSelf-citationChen, C. L. P., & Liu, Z. (2018) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2017.2716952 · Cited by 1,957
“MNIST data set [51].”
Metadata
- Authors
- Breuleux, O., Bengio, Y., & Vincent, P.
- Venue
- Neural Computation
- Publisher
- MIT Press - Journals
- Published
- 2011-08
- Volume
- 23
- Issue
- 8
- Pages
- 2058-2073
- ISSN
- 0899-7667 (ISSN-L)
- 1530-888X
- OpenAlex
- W2106439909
- Cited by
- 67
- References
- 2
- FWCI
- 5.56
- Type
- journal article
- Language
- en
- Open access
- closed
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Quickly Generating Representative Samples from an RBM-Derived Process. https://app.cochat.ai/papers/10.1162/neco_a_00158
- The paper
- Breuleux, O., Bengio, Y., & Vincent, P. (2011). Quickly Generating Representative Samples from an RBM-Derived Process. Neural Computation. https://doi.org/10.1162/neco_a_00158
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.