SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2303.06992 · ICLR · 2022

Improving Mutual Information Estimation with Annealed and Energy-Based Bounds

Greg Steeg, Rob Brekelmans, Roger Grosse, Marzyeh Ghassemi, Alireza Makhzani, Sicong Huang

arXiv · PDF · Open in the Atlas

Code that ran

3 of 7 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 2 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 1 failure of our instrument; 4 no recorded run), measured 2026-11-21; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2303.06992.json · badge: /api/ran/2303.06992.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
huangsicong/ais_mi_estimation canonical (classifier label)
classifier basis: classifier_2025
3 ran · 4 no recorded run
FunctionStatusWhere it lives
IWAE_loglikelihood_estimator Ran
ran, honoured the contract we drafted
huangsicong/ais_mi_estimation/codebase/algorithms/IWAE_estimators.py
pointer only (licence: NOASSERTION) · get_code("351fcc289f3f4dfe")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, huangsicong/ais_mi_estimation (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

conditional_H Ran
ran, honoured the contract we drafted
huangsicong/ais_mi_estimation/codebase/algorithms/mi_ais.py
pointer only (licence: NOASSERTION) · get_code("9d213e8a109b6228")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, huangsicong/ais_mi_estimation (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

log_normal_likelihood Ran
ran; our contract draft was wrong, not the code
huangsicong/ais_mi_estimation/codebase/algorithms/ais.py
pointer only (licence: NOASSERTION) · get_code("3456391452e4dd1e")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, huangsicong/ais_mi_estimation (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

AIS_core Not yet run
unverified (harvested, no recorded run)
huangsicong/ais_mi_estimation/codebase/algorithms/ais.py
pointer only (licence: NOASSERTION) · get_code("a9a30f84ae3b9d34")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, huangsicong/ais_mi_estimation (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

get_anneal_operators Not yet run
unverified (harvested, no recorded run)
huangsicong/ais_mi_estimation/codebase/algorithms/ais.py
pointer only (licence: NOASSERTION) · get_code("45639c4c9a9aff02")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, huangsicong/ais_mi_estimation (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

run_ais_chain_simplified Not yet run
unverified (harvested, no recorded run)
huangsicong/ais_mi_estimation/codebase/algorithms/ais.py
pointer only (licence: NOASSERTION) · get_code("25338c6bc7eaebc3")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, huangsicong/ais_mi_estimation (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

save_comparison Not yet run
unverified (harvested, no recorded run)
huangsicong/ais_mi_estimation/codebase/algorithms/ais.py
pointer only (licence: NOASSERTION) · get_code("191ead321aed5ede")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, huangsicong/ais_mi_estimation (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 7 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-21.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Mutual information (MI) is a fundamental quantity in information theory and machine learning. However, direct estimation of MI is intractable, even if the true joint probability density for the variables of interest is known, as it involves estimating a potentially high-dimensional log partition function. In this work, we present a unifying view of existing MI bounds from the perspective of importance sampling, and propose three novel bounds based on this approach. Since accurate estimation of MI without density information requires a sample size exponential in the true MI, we assume either a single marginal or the full joint density information is known. In settings where the full joint density is available, we propose Multi-Sample Annealed Importance Sampling (AIS) bounds on MI, which we demonstrate can tightly estimate large values of MI in our experiments. In settings where only a single marginal distribution is known, we propose Generalized IWAE (GIWAE) and MINE-AIS bounds. Our GIWAE bound unifies variational and contrastive bounds in a single framework that generalizes INFONCE, IWAE, and Barber-Agakov bounds. Our MINE-AIS method improves upon existing energy-based methods such as MINE-DV and MINE-F by directly optimizing a tighter lower bound on MI. MINE-AIS uses MCMC sampling to estimate gradients for training and Multi-Sample AIS for evaluating the bound. Our methods are particularly suitable for evaluating MI in deep generative models, since explicit forms of the marginal or joint densities are often available. We evaluate our bounds on estimating the MI of VAEs and GANs trained on the MNIST and CIFAR datasets, and showcase significant gains over existing bounds in these challenging settings with high ground truth MI.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2303.06992")
get_code_for_paper("2303.06992")
have("2303.06992")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2303.06992.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2303.06992.svg)](https://syntology.ai/paper/2303.06992)

Connect an agent — have() is free.