The DOI matches its Crossref record; 10 of the 10 references it cites were found in a registry or an index.
On the information bottleneck theory of deep learning*
Abstract
The practical successes of deep neural networks have not been matched by theoretical progress that satisfyingly explains their behavior. In this work, we study the information bottleneck (IB) theory of deep learning, which makes three specific claims: first, that deep networks undergo two distinct phases consisting of an initial fitting phase and a subsequent compression phase; second, that the compression phase is causally related to the excellent generalization performance of deep networks; and third, that the compression phase occurs due to the diffusion-like behavior of stochastic gradient descent. Here we show that none of these claims hold true in the general case, and instead reflect assumptions made to compute a finite mutual information metric in deterministic networks. When computed using simple binning, we demonstrate through a combination of analytical results and simulation that the information plane trajectory observed in prior work is predominantly a function of the neural nonlinearity employed: double-sided saturating nonlinearities like yield a compression phase as neural activations enter the saturation regime, but linear activation functions and single-sided saturating nonlinearities like the widely used ReLU in fact do not. Moreover, we find that there is no evident causal connection between compression and generalization: networks that do not compress are still capable of generalization, and vice versa. Next, we show that the compression phase, when it exists, does not arise from stochasticity in training by demonstrating that we can replicate the IB findings using full batch gradient descent rather than stochastic gradient descent. Finally, we show that when an input domain consists of a subset of task-relevant and task-irrelevant information, hidden representations do compress the task-irrelevant information, although the overall information about the input may monotonically increase with training time, and that this compression happens concurrently with the fitting process rather than during a subsequent compression period.
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
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Deep learning in neural networks: an overview
Schmidhuber, J. (2015) · Neural Networks · doi:10.1016/j.neunet.2014.09.003 · Cited by 18,570
Mastering the game of Go with deep neural networks and tree search
Silver, D., Huang, A., Maddison, C. J., Guez, A., Sifre, L., van den Driessche, G., Schrittwieser, J., Antonoglou, I., Panneershelvam, V., Lanctot, M., et al. (2016) · Nature · doi:10.1038/nature16961 · Cited by 15,612
Kraskov, A., Stögbauer, H., & Grassberger, P. (2004) · Physical Review E · doi:10.1103/physreve.69.066138 · Cited by 3,512
Deep learning and the information bottleneck principle
Tishby, N., & Zaslavsky, N. (2015) · 2015 IEEE Information Theory Workshop (ITW) · doi:10.1109/itw.2015.7133169 · Cited by 1,409
Neural networks and principal component analysis: Learning from examples without local minima
Baldi, P., & Hornik, K. (1989) · Neural Networks · doi:10.1016/0893-6080(89)90014-2 · Cited by 1,383
A Simple Coding Procedure Enhances a Neuron's Information Capacity
Laughlin, S. (1981) · Zeitschrift für Naturforschung C · doi:10.1515/znc-1981-9-1040 · Cited by 989
The Loss Surfaces of Multilayer Networks
Choromanska, A., Henaff, M., Mathieu, M., Arous, G. B., & LeCun, Y. (2014) · arXiv · doi:10.48550/arxiv.1412.0233 · Cited by 733
Why and when can deep-but not shallow-networks avoid the curse of dimensionality: A review
Poggio, T., Mhaskar, H., Rosasco, L., Miranda, B., & Liao, Q. (2017) · International Journal of Automation and Computing · doi:10.1007/s11633-017-1054-2 · Cited by 559
Statistical mechanics of learning from examples
Seung, H. S., Sompolinsky, H., & Tishby, N. (1992) · Physical Review A · doi:10.1103/physreva.45.6056 · Cited by 532
Cited by
Jusup, M., Holme, P., Kanazawa, K., Takayasu, M., Romić, I., Wang, Z., Geček, S., Lipić, T., Podobnik, B., Wang, L., et al. (2022) · Physics Reports · doi:10.1016/j.physrep.2021.10.005 · Cited by 643
Huang, X., Kroening, D., Ruan, W., Sharp, J., Sun, Y., Thamo, E., Wu, M., & Yi, X. (2020) · Computer Science Review · doi:10.1016/j.cosrev.2020.100270 · Cited by 532
Vali, A., Comai, S., & Matteucci, M. (2020) · Remote Sensing · doi:10.3390/rs12152495 · Cited by 455
To Tune or Not to Tune? Adapting Pretrained Representations to Diverse Tasks
Peters, M. E., Ruder, S., & Smith, N. A. (2019) · Proceedings of the 4th Workshop on Representation Learning for NLP (RepL4NLP-2019) · doi:10.18653/v1/w19-4302 · Cited by 432
Deep Semi-Supervised Anomaly Detection
Ruff, L., Vandermeulen, R. A., Görnitz, N., Binder, A., Müller, E., Müller, K.-R., & Kloft, M. (2019) · arXiv · doi:10.48550/arxiv.1906.02694 · Cited by 388
Metadata
- Authors
- Saxe, A. M., Bansal, Y., Dapello, J., Advani, M., Kolchinsky, A., Tracey, B. D., & Cox, D. D.
- Venue
- Journal of Statistical Mechanics: Theory and Experiment
- Publisher
- IOP Publishing
- Published
- 2019-12-01
- Volume
- 2019
- Issue
- 12
- Pages
- 124020
- ISSN
- 1742-5468 (ISSN-L)
- OpenAlex
- W2785885194
- Cited by
- 493
- References
- 10
- FWCI
- 30.74
- 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: On the information bottleneck theory of deep learning*. https://app.cochat.ai/papers/10.1088/1742-5468/ab3985
- The paper
- Saxe, A. M., Bansal, Y., Dapello, J., Advani, M., Kolchinsky, A., Tracey, B. D., & Cox, D. D. (2019). On the information bottleneck theory of deep learning*. Journal of Statistical Mechanics: Theory and Experiment. https://doi.org/10.1088/1742-5468/ab3985
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.