Papers › Towards a Neural Statistician

Towards a Neural Statistician

7 Jun 2016arXiv:1606.02185archive 2025-07-28

Harrison Edwards, Amos Storkey

An efficient learner is one who reuses what they already know to tackle a new problem. For a machine learner, this means understanding the similarities amongst datasets. In order to do this, one must take seriously the idea of working with datasets, rather than datapoints, as the key objects to model. Towards this goal, we demonstrate an extension of a variational autoencoder that can learn a method for computing representations, or statistics, of datasets in an unsupervised fashion. The network is trained to produce statistics that encapsulate a generative model for each dataset. Hence the network enables efficient learning from new datasets for both unsupervised and supervised tasks. We show that we are able to learn statistics that can be used for: clustering datasets, transferring generative models to new datasets, selecting representative samples of datasets and classifying previously unseen classes. We refer to our model as a neural statistician, and by this we mean a neural network that can learn to compute summary statistics of datasets without supervision.

PaperPDFCodeCode Syntology ran

In Syntology 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="1606.02185")

Code

Syntology Ran 2 of 14 code samples harvested from 2 repositories linked to this paper; 12 have no recorded run. Of those that ran: 2 ran with no contract checked.

By repository: community (archive-listed): 14 samples from 2 repositories, 2 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

comramona/neural-statistician mentioned on GitHubpytorch report
conormdurkan/neural-statistician mentioned on GitHubpytorch report
cravingoxygen/neuralstat mentioned on GitHubpytorchMIT report
htso/Pedestrian_in_few_shots mentioned on GitHubpytorch report
lupalab/flowscan mentioned on GitHubtfMIT 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

14 samples harvested; 2 ran; 0 honoured the contract we drafted; 12 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

2ran
12unverified

Licence: 0 of the 14 samples are 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 2 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.

pca cravingoxygen/neuralstat/tsne.py community (archive-listed) ran fingerprinted MIT (permissive) · f60cb3cead55f81b · report
x2p cravingoxygen/neuralstat/tsne.py community (archive-listed) ran fingerprinted MIT (permissive) · 654e67f1bec03fc8 · report
Hbeta cravingoxygen/neuralstat/tsne.py community (archive-listed) unverified MIT (permissive) · 77fb404ad78a22d9 · report
apply_batch_norm cravingoxygen/neuralstat/spatial_mnist.py community (archive-listed) unverified MIT (permissive) · 6913afa4a65fe7f8 · report
gaussian_log_likelihood cravingoxygen/neuralstat/tests.py community (archive-listed) unverified MIT (permissive) · 2e7d466cc00bbeab · report
generate_samples_like cravingoxygen/neuralstat/spatial_mnist.py community (archive-listed) unverified MIT (permissive) · 7e9c25119c6905fb · report
independent_model lupalab/flowscan/model/conditionals.py community (archive-listed) unverified MIT (permissive) · 95f11ad1d1b6f501 · report
load_images cravingoxygen/neuralstat/spatialcreate.py community (archive-listed) unverified MIT (permissive) · 5c72e16208cff35c · report
load_labels cravingoxygen/neuralstat/spatialcreate.py community (archive-listed) unverified MIT (permissive) · b1af56804ab57958 · report
main lupalab/flowscan/demos/flowscan_demo.py community (archive-listed) unverified MIT (permissive) · b2874edcc99ce4e6 · report
make_in_out lupalab/flowscan/model/conditionals.py community (archive-listed) unverified MIT (permissive) · 6625ee33e78ed05d · report
mixture_of_mixtures lupalab/flowscan/model/likelihoods.py community (archive-listed) unverified MIT (permissive) · d96984eb51ffcaa1 · report
new_mixture_of_mixtures lupalab/flowscan/model/likelihoods.py community (archive-listed) unverified MIT (permissive) · 9c2927a6cb5b2667 · report
sample_mm lupalab/flowscan/model/conditionals.py community (archive-listed) unverified MIT (permissive) · dffe6cbc0b246e38 · report

Tasks

ClusteringFew-Shot Image Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Few-Shot Image Classification OMNIGLOT - 1-Shot, 20-way Neural Statistician Accuracy 93.2% #16 of 20 Archive leaderboard report
Few-Shot Image Classification OMNIGLOT - 1-Shot, 5-way Neural Statistician Accuracy 98.1 #15 of 17 Archive leaderboard report
Few-Shot Image Classification OMNIGLOT - 5-Shot, 20-way Neural Statistician Accuracy 98.1% #16 of 19 Archive leaderboard report
Few-Shot Image Classification OMNIGLOT - 5-Shot, 5-way Neural Statistician Accuracy 99.5 #12 of 16 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

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