The DOI matches its Crossref record; 10 of the 10 references it cites were found in a registry or an index.
Deep learning and the information bottleneck principle
Open accessAbstract
Deep Neural Networks (DNNs) are analyzed via the theoretical framework of the information bottleneck (IB) principle. We first show that any DNN can be quantified by the mutual information between the layers and the input and output variables. Using this representation we can calculate the optimal information theoretic limits of the DNN and obtain finite sample generalization bounds. The advantage of getting closer to the theoretical limit is quantifiable both by the generalization bound and by the network's simplicity. We argue that both the optimal architecture, number of layers and features/connections at each layer, are related to the bifurcation points of the information bottleneck tradeoff, namely, relevant compression of the input layer with respect to the output layer. The hierarchical representations at the layered network naturally correspond to the structural phase transitions along the information curve. We believe that this new insight can lead to new optimality bounds and deep learning algorithms.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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
Elements of Information Theory
Cover, T. M., & Thomas, J. A. (2001) · Wiley eBooks · doi:10.1002/0471200611 · Cited by 36,808
Reducing the dimensionality of data with neural networks
Hinton, G. E., & Salakhutdinov, R. R. (2006) · Science · doi:10.1126/science.1127647 · Cited by 20,928
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
Learning Deep Architectures for AI
Bengio, Y. (2009) · Foundations and Trends® in Machine Learning · doi:10.1561/2200000006 · Cited by 6,938
The information bottleneck method
Tishby, N., Pereira, F. C., & Bialek, W. (2000) · arXiv · doi:10.48550/arxiv.physics/0004057 · Cited by 2,626 · cited 2×
“As was shown in [6], the optimal solutions for the IB variational problem satisfy the following self-consistent equations for some value of β , where Z ( x ; β ) is the normalization factor, also known as the partition function.”
MethodSelf-citationRose, K. (1998) · Proceedings of the IEEE · doi:10.1109/5.726788 · Cited by 876
Statistical mechanics and phase transitions in clustering
Rose, K., Gurewitz, E., & Fox, G. C. (1990) · Physical Review Letters · doi:10.1103/physrevlett.65.945 · Cited by 458
An exact mapping between the Variational Renormalization Group and Deep LearningPreprint
Mehta, P., & Schwab, D. J. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1410.3831 · Cited by 421
Learning and generalization with the information bottleneck
Shamir, O., Sabato, S., & Tishby, N. (2010) · Theoretical Computer Science · doi:10.1016/j.tcs.2010.04.006 · Cited by 165
Self-citationAn Information Theoretic Tradeoff between Complexity and Accuracy
Gilad-Bachrach, R., Navot, A., & Tishby, N. (2003) · Lecture notes in computer science · doi:10.1007/978-3-540-45167-9_43 · Cited by 99
Self-citation
Cited by
YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information
Wang, C.-Y., Yeh, I.-H., & Mark Liao, H.-Y. (2025) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-72751-1_1 · Cited by 4,823
A Survey on Explainable Artificial Intelligence (XAI): Toward Medical XAI
Tjoa, E., & Guan, C. (2021) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2020.3027314 · Cited by 2,524
Machine Learning in Drug Discovery: A Review
Dara, S., Dhamercherla, S., Jadav, S. S., Babu, C. M., & Ahsan, M. J. (2022) · Artificial Intelligence Review · doi:10.1007/s10462-021-10058-4 · Cited by 792
Neural Sign Language Translation
Camgoz, N. C., Hadfield, S., Koller, O., Ney, H., & Bowden, R. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00812 · Cited by 784
Barlow Twins: Self-Supervised Learning via Redundancy Reduction
Žbontar, J., Jing, L., Misra, I., LeCun, Y., & Deny, S. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.03230 · Cited by 751
Metadata
- Authors
- Tishby, N., & Zaslavsky, N.
- Venue
- 2015 IEEE Information Theory Workshop (ITW)
- Publisher
- IEEE
- Published
- 2015-04
- Pages
- 1-5
- OpenAlex
- W2096516049
- Cited by
- 1,409
- References
- 10
- FWCI
- 18.37
- Type
- conference paper
- Language
- en
- Open access
- green
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: Deep learning and the information bottleneck principle. https://app.cochat.ai/papers/10.1109/itw.2015.7133169
- The paper
- Tishby, N., & Zaslavsky, N. (2015). Deep learning and the information bottleneck principle. 2015 IEEE Information Theory Workshop (ITW). https://doi.org/10.1109/itw.2015.7133169
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.