Papers › Learning Compressed Transforms with Low Displacement Rank

Learning Compressed Transforms with Low Displacement Rank

4 Oct 2018NeurIPS 2018 12arXiv:1810.02309archive 2025-07-28

Anna T. Thomas, Albert Gu, Tri Dao, Atri Rudra, Christopher Ré

The low displacement rank (LDR) framework for structured matrices represents a matrix through two displacement operators and a low-rank residual. Existing use of LDR matrices in deep learning has applied fixed displacement operators encoding forms of shift invariance akin to convolutions. We introduce a class of LDR matrices with more general displacement operators, and explicitly learn over both the operators and the low-rank component. This class generalizes several previous constructions while preserving compression and efficient computation. We prove bounds on the VC dimension of multi-layer neural networks with structured weight matrices and show empirically that our compact parameterization can reduce the sample complexity of learning. When replacing weight layers in fully-connected, convolutional, and recurrent neural networks for image classification and language modeling tasks, our new classes exceed the accuracy of existing compression approaches, and on some tasks also outperform general unstructured layers while using more than 20x fewer parameters.

PaperPDFConference PDFCodeCode Syntology ran

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):

Code

Syntology 21 code samples harvested from 1 repository linked to this paper: 10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 11 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 21 samples from 1 repository, 10 ran (10 with no instrument failure; 0 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.

Levels written on 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

HazyResearch/structured-nets officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 21 samples, 10 ran (0 instrument-failed) · 11 unverified 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: 10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 11 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.

10ran
11unverified

Licence: 0 of the 21 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 HazyResearch/structured-nets. “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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

HazyResearch/structured-nets official repository 21 samples, 10 ran (0 instrument-failed) · 11 unverified
circ_diag_transpose_mult_fn tensorflow/krylov.py ran Apache-2.0 (permissive) · 93114c4a7dcf4c7e · report fixture: signature v_f:EagerTensor/1/float, d:EagerTensor/1/float, x:EagerTensor/1/float, n:int/0/int · returned EagerTensor · level recorded 2026-09-25
circ_transpose_mult_fn tensorflow/krylov.py ran Apache-2.0 (permissive) · db48787ad55ef7af · report fixture: signature v_f:EagerTensor/1/float, x:EagerTensor/1/float, n:int/0/int · returned EagerTensor · level recorded 2026-09-25
construct_model in 11 papers pytorch/models/nets.py ran Apache-2.0 (permissive) · f16e103b2cd798b5 · report fixture: signature cls:callable/0/?, in_size:int/0/int, out_size:int/0/int, args:MockArgs/0/? · returned SimpleModel · level recorded 2026-09-25
create_command tensorflow/compare_parallel.py ran Apache-2.0 (permissive) · b1be7db8436ba3d5 · report fixture: signature args:Namespace/0/?, method:str/0/str, rank:int/0/int, lr:float/0/float, decay_rate:float/0/float, mom:float/0/float · returned str · level recorded 2026-09-25
cross_entropy_loss in 58 papers pytorch/utils.py ran fingerprinted Apache-2.0 (permissive) · 8ef54cdb8384cbab · report fixture: signature pred:Tensor/2/float, true:Tensor/2/float · returned tuple · level recorded 2026-09-25
descendants pytorch/utils.py ran Apache-2.0 (permissive) · da5caff101ceaca4 · report fixture: signature cls:callable/0/? · returned list · level recorded 2026-09-25
get_dataset in 285 papers pytorch/dataset.py ran Apache-2.0 (permissive) · caeffaa5677b8ac4 · report fixture: signature dataset_name:str/0/str, data_dir:str/0/str, transform:str/0/str · returned tuple · level recorded 2026-09-25
identity_mult_fn tensorflow/krylov.py ran fingerprinted Apache-2.0 (permissive) · 143fa9ec9a47925c · report fixture: signature v:Tensor/2/float, n:int/0/int · returned Tensor · level recorded 2026-09-25
mse_loss in 73 papers
census: 8 implementations from 12 papers, 6 distinct outputs across 4 buckets, one shared input per bucket
pytorch/utils.py ran fingerprinted Apache-2.0 (permissive) · 77458eee7fb25de2 · report fixture: signature pred:Tensor/2/float, true:Tensor/2/float · returned tuple · level recorded 2026-09-25
split_train_val in 5 papers pytorch/dataset.py ran Apache-2.0 (permissive) · fe4c30a21b8a8bc7 · report fixture: signature train_X:Tensor/2/float, train_Y:Tensor/2/float, val_fraction:float/0/float, train_fraction:NoneType/0/? · returned tuple · level recorded 2026-09-25
StructuredLinear pytorch/structure/layer.py unverified Apache-2.0 (permissive) · 03ab2af9fe40e057 · report
check_rank tensorflow/model.py unverified Apache-2.0 (permissive) · cae5d71738786dfd · report
circulant_sparsity tensorflow/learned_operators.py unverified Apache-2.0 (permissive) · b42d372b234d35de · report
create_data_loaders pytorch/dataset.py unverified Apache-2.0 (permissive) · 57fe2dad04e97dae · report
forward in 75 papers tensorflow/model.py unverified Apache-2.0 (permissive) · 948d6e2b3de233d3 · report
get_structured_W tensorflow/model.py unverified Apache-2.0 (permissive) · 769fab47f27b89f1 · report
hankel_like tensorflow/fixed_operators.py unverified Apache-2.0 (permissive) · fb5f1ea3206617c6 · report
polynomial_transform tensorflow/learned_operators.py unverified Apache-2.0 (permissive) · c4119d98ae620aa5 · report
toeplitz_like tensorflow/fixed_operators.py unverified Apache-2.0 (permissive) · f6411433b636f6e4 · report
tridiagonal_corner tensorflow/learned_operators.py unverified Apache-2.0 (permissive) · 68475184587cb150 · report
vandermonde_like tensorflow/fixed_operators.py unverified Apache-2.0 (permissive) · 63f703ee8d1bd7fb · report

Tasks

Image ClassificationLanguage ModelingLanguage Modellingimage-classification

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