Papers › The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks
The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks
Jonathan Frankle, Michael Carbin
Neural network pruning techniques can reduce the parameter counts of trained networks by over 90%, decreasing storage requirements and improving computational performance of inference without compromising accuracy. However, contemporary experience is that the sparse architectures produced by pruning are difficult to train from the start, which would similarly improve training performance. We find that a standard pruning technique naturally uncovers subnetworks whose initializations made them capable of training effectively. Based on these results, we articulate the "lottery ticket hypothesis:" dense, randomly-initialized, feed-forward networks contain subnetworks ("winning tickets") that - when trained in isolation - reach test accuracy comparable to the original network in a similar number of iterations. The winning tickets we find have won the initialization lottery: their connections have initial weights that make training particularly effective. We present an algorithm to identify winning tickets and a series of experiments that support the lottery ticket hypothesis and the importance of these fortuitous initializations. We consistently find winning tickets that are less than 10-20% of the size of several fully-connected and convolutional feed-forward architectures for MNIST and CIFAR10. Above this size, the winning tickets that we find learn faster than the original network and reach higher test accuracy.
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):
get_harvested_code_for_paper(arxiv_id="1803.03635")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="1803.03635", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="1803.03635")
Code
Syntology 25 code samples harvested from 14 repositories linked to this paper: 12 ran (of which 2 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 13 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.
By repository: community (archive-listed): 25 samples from 14 repositories, 12 ran (10 with no instrument failure; 2 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.
No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:
- uber-research/deconstructing-lottery-tickets, community (archive-listed): harvested for another paper, listed under the repository
Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.
24 repositories listed; official and paper-mentioned ones first.
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.
A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.
Code Syntology ran Syntology
25 samples harvested: 12 ran (of which 2 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 13 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.
Licence: 6 of the 25 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 14 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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.
239b1c9179d0f205 · report
c3736538f6336cc1 · report
fixture: returned list · level recorded 2026-09-22 85ad362a20ae6e7b · report
dec7df8ba96b72cf · report
fixture: signature ndarray:ndarray/2/float · returned float · level recorded 2026-09-26 29318b74de85a6a7 · report
fixture: signature layer:callable/0/? · returned bool · level recorded 2026-09-26 4a68efa34f4d9a4d · report
fixture: signature ndarray:ndarray/2/float, target_sparsity:float/0/float · returned ndarray · level recorded 2026-09-26 429d1495da51432a · report
d55e91d5c465a514 · report
affcc14cf097faad · report
83ea615b3cdbcc44 · report
fixture: returned PruneNN · level recorded 2026-09-22 03bcd1b2149937aa · report
fixture: signature parent_directory:str/0/str · returned str · level recorded 2026-09-26 55dac1ab0b434f50 · report
fixture: signature parent_directory:str/0/str · returned str · level recorded 2026-09-26 d9c4c8964d1fac64 · report
fixture: signature parent_directory:str/0/str · returned str · level recorded 2026-09-26 f85f16caefd6b8eb · report
fixture: signature percents:dict/0/?, masks:dict/0/?, final_weights:dict/0/? · returned dict · level recorded 2026-09-26 f8f55fc872e42472 · report
fixture: signature network:dict/0/?, combine_fn:callable/0/? · returned dict · level recorded 2026-09-26 c64600650ffbbe46 · report
1a27a9779b4642f9 · report
f4efe6bc7f43e9a5 · report
fixture: signature model:callable/0/?, output_class:int/0/int, bias:bool/0/bool, linear:float/0/float, output:float/0/float, conv:float/0/float, batchnorm:float/0/float · returned SmallModel · level recorded 2026-09-22 615a98f5356e6e36 · report
fixture: returned MaskedDense · level recorded 2026-09-22 174ea0f086b238ab · report
37d9fe25cec668ef · report
2c4ad9ac492a7e53 · report
d5df1b38c4aef4a5 · report
Method as code Syntology
What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.
12 assemblies on this paper: 12 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).
12 sibling assemblies for The Lottery Ticket Hypothesis (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.
harvested Assembly for The Lottery Ticket Hypothesis (graph method: The Lottery Ticket Hypothesis). 1 brick; individually on a fixture: 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. The assembly has not been run end-to-end.
one of 12 siblings
- lth_global_unstructured_pruning entry · level 1 · ran · our draft was wrong ·
f4efe6bc7f43e9a5
harvested Assembly for The Lottery Ticket Hypothesis (graph method: The Lottery Ticket Hypothesis). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.
one of 12 siblings
- prune entry · level 0 · unverified ·
affcc14cf097faad
harvested Assembly for The Lottery Ticket Hypothesis (graph method: The Lottery Ticket Hypothesis). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.
one of 12 siblings
- main entry · level 0 · unverified ·
37d9fe25cec668ef
harvested Assembly for The Lottery Ticket Hypothesis (graph method: The Lottery Ticket Hypothesis). 2 bricks; individually on a fixture: 0 ran · 2 unverified. The assembly has not been run end-to-end.
one of 12 siblings
- prune_mlp entry · level 0 · unverified ·
d5df1b38c4aef4a5 - prune_linear helper · level 0 · unverified ·
2c4ad9ac492a7e53
harvested Assembly for The Lottery Ticket Hypothesis (graph method: The Lottery Ticket Hypothesis). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.
one of 12 siblings
- prune_network entry · level 0 · unverified ·
85ad362a20ae6e7b
harvested Assembly for The Lottery Ticket Hypothesis (graph method: The Lottery Ticket Hypothesis). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.
one of 12 siblings
- prune_model entry · level 0 · unverified ·
1a27a9779b4642f9
harvested Assembly for The Lottery Ticket Hypothesis (graph method: The Lottery Ticket Hypothesis). 2 bricks; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.
one of 12 siblings
- PruneNN entry · level 1 · ran ·
83ea615b3cdbcc44 - init_weights helper · level 0 · unverified ·
6ee14debe7b75591
harvested Assembly for The Lottery Ticket Hypothesis (graph method: The Lottery Ticket Hypothesis). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.
one of 12 siblings
- pruning_model entry · level 0 · unverified ·
174ea0f086b238ab
harvested Assembly for The Lottery Ticket Hypothesis (graph method: The Lottery Ticket Hypothesis). 1 brick; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.
one of 12 siblings
- MaskedDense entry · level 1 · ran ·
615a98f5356e6e36
harvested Assembly for The Lottery Ticket Hypothesis (graph method: The Lottery Ticket Hypothesis). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.
one of 12 siblings
- experiment entry · level 0 · unverified ·
239b1c9179d0f205
harvested Assembly for The Lottery Ticket Hypothesis (graph method: The Lottery Ticket Hypothesis). 3 bricks; individually on a fixture: 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.
one of 12 siblings
- SmartRatio entry · level 1 · ran; the contract check could not run (RAISES) ·
c3736538f6336cc1 - count_fc_parameters helper · level 1 · ran · honoured contract ·
dd41a92a0afa4fd7 - count_total_parameters helper · level 1 · ran · honoured contract ·
155c0c245324ce36
harvested Assembly for The Lottery Ticket Hypothesis (graph method: The Lottery Ticket Hypothesis). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.
one of 12 siblings
- LotteryModel entry · level 0 · unverified ·
5ca323d31d0cded6
Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="1803.03635") returns these assemblies with each brick's role and wiring (how to connect).
Tasks
Results from the paper archive 2025-07-28
No leaderboard rows for this paper in the archive.
Methods
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