Papers › How Does Information Bottleneck Help Deep Learning?

How Does Information Bottleneck Help Deep Learning?

30 May 2023arXiv:2305.18887archive 2025-07-28

Kenji Kawaguchi, Zhun Deng, Xu Ji, Jiaoyang Huang

Numerous deep learning algorithms have been inspired by and understood via the notion of information bottleneck, where unnecessary information is (often implicitly) minimized while task-relevant information is maximized. However, a rigorous argument for justifying why it is desirable to control information bottlenecks has been elusive. In this paper, we provide the first rigorous learning theory for justifying the benefit of information bottleneck in deep learning by mathematically relating information bottleneck to generalization errors. Our theory proves that controlling information bottleneck is one way to control generalization errors in deep learning, although it is not the only or necessary way. We investigate the merit of our new mathematical findings with experiments across a range of architectures and learning settings. In many cases, generalization errors are shown to correlate with the degree of information bottleneck: i.e., the amount of the unnecessary information at hidden layers. This paper provides a theoretical foundation for current and future methods through the lens of information bottleneck. Our new generalization bounds scale with the degree of information bottleneck, unlike the previous bounds that scale with the number of parameters, VC dimension, Rademacher complexity, stability or robustness. Our code is publicly available at: https://github.com/xu-ji/information-bottleneck

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 13 code samples harvested from 1 repository linked to this paper: 8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 13 samples from 1 repository, 8 ran (8 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-24 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

xu-ji/information-bottleneck officialmentioned in papermentioned on GitHubpytorchBSD-2-ClauseSyntology: 13 samples, 8 ran (0 instrument-failed) · 5 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

13 samples harvested: 8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

8ran
5unverified

Licence: 3 of the 13 samples are pointer only, meaning Syntology does not serve that copy's text. For 3 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from xu-ji/information-bottleneck. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

xu-ji/information-bottleneck official repository 13 samples, 8 ran (0 instrument-failed) · 5 unverified
adversarial_cross_entropy dnn/swag_repo/swag/losses.py ran BSD-2-Clause (permissive) here; the stored copy is pointer only · e11996f54eea8253 · report fixture: signature model:callable/0/?, input:Tensor/2/float, target:Tensor/1/int, lossfn:callable/0/?, epsilon:float/0/float · returned tuple · level recorded 2026-09-24
compute_MI_theta_D_single_seed_jensen toy/util/swag.py ran BSD-2-Clause (permissive) · 962fc1c520aa6c6a · report fixture: signature swag_models:list/1/callable, num_samples:int/0/int, layers:list/1/int · returned Tensor · level recorded 2026-09-26
cross_entropy in 92 papers
census: 6 implementations from 8 papers, 5 distinct outputs across 2 buckets, one shared input per bucket
dnn/swag_repo/swag/losses.py ran BSD-2-Clause (permissive) here; the stored copy is pointer only · fc2aaf6fd20bc53f · report fixture: signature model:callable/0/?, input:Tensor/2/float, target:Tensor/1/int · returned tuple · level recorded 2026-09-24
dataset_name dnn/swag_repo/MI/util.py ran BSD-2-Clause (permissive) · 5e26fa10c5a96c83 · report fixture: signature data:str/0/str, seed:int/0/int, i:int/0/int · returned str · level recorded 2026-09-26
est_MI toy/util/general.py ran BSD-2-Clause (permissive) · 43703d6b3f57375b · report fixture: signature model:callable/0/?, dataset:list/1/tuple, sz:int/0/int, jensen:bool/0/bool, requires_grad:bool/0/bool · returned Tensor · level recorded 2026-09-26
est_MI_cond toy/util/general.py ran BSD-2-Clause (permissive) · dfa889418df10f6f · report fixture: signature model:callable/0/?, num_classes:int/0/int, dl:list/1/tuple, sz:int/0/int, jensen:bool/0/bool · returned Tensor · level recorded 2026-09-26
exp_name dnn/swag_repo/MI/util.py ran BSD-2-Clause (permissive) · 9f5a910348a7492a · report fixture: signature args:Args/0/? · returned str · level recorded 2026-09-26
exp_name_flat dnn/swag_repo/MI/util.py ran BSD-2-Clause (permissive) · 36461b9533fa5d2f · report fixture: signature dataset:str/0/str, seed:int/0/int, batch_size:int/0/int, wd:float/0/float, model:str/0/str · returned str · level recorded 2026-09-26
basic_data toy/util/data.py unverified BSD-2-Clause (permissive) · 661a8c2abca9d4d4 · report
basic_data_instance toy/util/data.py unverified BSD-2-Clause (permissive) · a0d8e4386d7c5fbd · report
loaders dnn/swag_repo/experiments/imagenet/data.py unverified BSD-2-Clause (permissive) · 99e3815602045644 · report
masked_loss in 8 papers dnn/swag_repo/swag/losses.py unverified BSD-2-Clause (permissive) here; the stored copy is pointer only · 8bbca7799326d580 · report
train_model in 103 papers toy/util/general.py unverified BSD-2-Clause (permissive) · 802ae9c8c6458aaf · report

Tasks

Deep LearningGeneralization BoundsLearning Theory

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections