Papers › On Variational Bounds of Mutual Information

On Variational Bounds of Mutual Information

16 May 2019arXiv:1905.06922archive 2025-07-28

Ben Poole, Sherjil Ozair, Aaron van den Oord, Alexander A. Alemi, George Tucker

Estimating and optimizing Mutual Information (MI) is core to many problems in machine learning; however, bounding MI in high dimensions is challenging. To establish tractable and scalable objectives, recent work has turned to variational bounds parameterized by neural networks, but the relationships and tradeoffs between these bounds remains unclear. In this work, we unify these recent developments in a single framework. We find that the existing variational lower bounds degrade when the MI is large, exhibiting either high bias or high variance. To address this problem, we introduce a continuum of lower bounds that encompasses previous bounds and flexibly trades off bias and variance. On high-dimensional, controlled problems, we empirically characterize the bias and variance of the bounds and their gradients and demonstrate the effectiveness of our new bounds for estimation and representation learning.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1905.06922")

Code

Syntology Ran 17 of 21 code samples harvested from 3 repositories linked to this paper; 4 have no recorded run. Of those that ran: 1 ran · our draft was wrong; 16 ran with no contract checked.

By repository: community (archive-listed): 21 samples from 3 repositories, 17 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Linear95/CLUB mentioned on GitHubtf report
RSMI-NE/RSMI-NE mentioned on GitHubtfApache-2.0 report
karlstratos/doe mentioned on GitHubpytorch 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

21 samples harvested; 17 ran; 0 honoured the contract we drafted; 4 have no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

1ran · our draft was wrong
16ran
4unverified

Licence: 1 of the 21 samples is pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 3 repositories linked to this paper, official or community; each sample names its own and says which. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

CLUB Linear95/CLUB/mi_estimators.py community (archive-listed) ran · metamorphic tier: deterministic no licence file found · pointer only · 5d0591b944022c57 · report
Interpolated karlstratos/doe/util.py community (archive-listed) ran MIT (permissive) · d12ee8538feed408 · report
LnConstant karlstratos/doe/util.py community (archive-listed) ran · metamorphic tier: invariant fingerprinted MIT (permissive) · 0025679c7875a0c7 · report
LnStandardNormal karlstratos/doe/util.py community (archive-listed) ran · metamorphic tier: invariant MIT (permissive) · 2e3c4ed92aa3a733 · report
RSMI_estimate RSMI-NE/RSMI-NE/rsmine/coarsegrainer/cg_optimisers.py community (archive-listed) ran fingerprinted Apache-2.0 (permissive) · 6e2da11b3259438f · report
RSMIdat_filename RSMI-NE/RSMI-NE/rsmine/coarsegrainer/build_dataset.py community (archive-listed) ran Apache-2.0 (permissive) · 437b404161244763 · report
array2tensor RSMI-NE/RSMI-NE/rsmine/coarsegrainer/cg_utils.py community (archive-listed) ran Apache-2.0 (permissive) · 4183e7ff2acbf08b · report
connect_bbox RSMI-NE/RSMI-NE/rsmine/coarsegrainer/plotter.py community (archive-listed) ran Apache-2.0 (permissive) · aaece4f3948487e3 · report
construct_reference_graph RSMI-NE/RSMI-NE/rsmine/coarsegrainer/cg_utils.py community (archive-listed) ran Apache-2.0 (permissive) · addf3c7443f250de · report
eids_from_edges RSMI-NE/RSMI-NE/rsmine/coarsegrainer/analysis_utils.py community (archive-listed) ran Apache-2.0 (permissive) · 76a7c4299deb0214 · report
filename RSMI-NE/RSMI-NE/rsmine/coarsegrainer/build_dataset.py community (archive-listed) ran Apache-2.0 (permissive) · 1bf1efc3800ca8ce · report
get_ln_score_function karlstratos/doe/util.py community (archive-listed) ran · our draft was wrong MIT (permissive) · f13e85f7d9e6310c · report
iter_loadtxt RSMI-NE/RSMI-NE/rsmine/coarsegrainer/build_dataset.py community (archive-listed) ran Apache-2.0 (permissive) · 7b89f9242dbba472 · report
loadNSplit_DimerandVBS RSMI-NE/RSMI-NE/rsmine/coarsegrainer/cg_utils.py community (archive-listed) ran Apache-2.0 (permissive) · 9ef4718a1e2a6699 · report
non_collapsed_data RSMI-NE/RSMI-NE/rsmine/coarsegrainer/analysis_utils.py community (archive-listed) ran Apache-2.0 (permissive) · 958a914e73170a8f · report
non_collapsed_estimates RSMI-NE/RSMI-NE/rsmine/coarsegrainer/analysis_utils.py community (archive-listed) ran Apache-2.0 (permissive) · 5c3a5208a2efd5f1 · report
round_up RSMI-NE/RSMI-NE/rsmine/coarsegrainer/plotter.py community (archive-listed) ran fingerprinted Apache-2.0 (permissive) · 1b4c5ecd9ab8505e · report
FF karlstratos/doe/util.py community (archive-listed) unverified MIT (permissive) · b344d686dec45a3b · report
cg_configs RSMI-NE/RSMI-NE/rsmine/coarsegrainer/cg_sequels.py community (archive-listed) unverified Apache-2.0 (permissive) · 3a4cb53a40962c2b · report
correlator RSMI-NE/RSMI-NE/rsmine/coarsegrainer/cg_sequels.py community (archive-listed) unverified Apache-2.0 (permissive) · 8c47f52617901f50 · report
mark_inset_hack RSMI-NE/RSMI-NE/rsmine/coarsegrainer/plotter.py community (archive-listed) unverified Apache-2.0 (permissive) · 1396b54f81fa12c7 · report

Tasks

Representation Learning

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