Methods › General › Active Learning › Snapshot Ensembles
Snapshot Ensembles: Train 1, get M for free
Snapshot Ensembles
Introduced by Gao Huang et al. in Snapshot Ensembles: Train 1, get M for free
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
The overhead cost of training multiple deep neural networks could be very high in terms of the training time, hardware, and computational resource requirement and often acts as obstacle for creating deep ensembles. To overcome these barriers Huang et al. proposed a unique method to create ensemble which at the cost of training one model, yields multiple constituent model snapshots that can be ensembled together to create a strong learner. The core idea behind the concept is to make the model converge to several local minima along the optimization path and save the model parameters at these local minima points. During the training phase, a neural network would traverse through many such points. The lowest of all such local minima is known as the Global Minima. The larger the model, more are the number of parameters and larger the number of local minima points. This implies, there are discrete sets of weights and biases, at which the model is making fewer errors. So, every such minimum can be considered a weak but a potential learner model for the problem being solved. Multiple such snapshot of weights and biases are recorded which can later be ensembled to get a better generalized model which makes the least amount of mistakes.
In Syntology harvested code stored, below machine verification (unverified_code; harvested), served level V1; retrieve with get_harvested_code_for_paper(arxiv_id='1704.00109'). Repositories: 11 listed of 11 in the graph, strongest link: official. The lookup matched a paper by its title, arXiv:1704.00109, not a method entry. This answer is about arXiv:1704.00109, the paper the archive credits with this method.
Origin paper of this answer, arXiv:1704.00109 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample). The instrument figure counts failures of Syntology's instrument, not of the code. Ran means executed on a synthesized input, not that the code is correct.
Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.
What each level means, quoted from Syntology's server card: V0 “imports”; V1 “executes against a synthesized fixture and returns a value of the recorded type”; V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” The card adds: “No rung on this ladder compares the served code against the authors' implementation, so treat every level as evidence about runnability and internal agreement, not about matching the paper's results.” A level quoted in two parts is one definition the card writes as two clauses joined by a double hyphen, each clause quoted on its own (how these levels are quoted).
Papers archive 2025-07-28
archive papers tagged: 8 · with a code link: 5 · where Syntology ran a sample: 3 (2 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (3 of 8 tagged: 2 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 8 of 8, newest first by the archive's date (ties by slug), in archive order.
Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.
-
SnapE -- Training Snapshot Ensembles of Link Prediction Models 5 Aug 2024 · 0 repositories · arXiv:2408.02707
-
To Stay or Not to Stay in the Pre-train Basin: Insights on Ensembling in Transfer Learning 6 Mar 2023 · 1 repository · arXiv:2303.03374Syntology official (archive's flag): 2 ran · 2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result (of 2 harvested samples) · 2 pointer-only (licence)
-
Interpretable Diversity Analysis: Visualizing Feature Representations In Low-Cost Ensembles 12 Feb 2023 · 0 repositories · arXiv:2302.05822
-
Malaria Parasite Detection using Efficient Neural Ensembles 15 Oct 2021 · 1 repository
-
Accuracy-Privacy Trade-off in Deep Ensemble: A Membership Inference Perspective 12 May 2021 · 1 repository · arXiv:2105.05381
-
MotherNets: Rapid Deep Ensemble Learning 12 Sep 2018 · 0 repositories · arXiv:1809.04270
-
Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs 27 Feb 2018 · 8 repositories · arXiv:1802.10026Syntology community repositories only · 8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified (of 14 harvested samples)
-
Snapshot Ensembles: Train 1, get M for free 1 Apr 2017 · 11 repositories · arXiv:1704.00109Syntology community repositories only · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)
Tasks archive 2025-07-28
13 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
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