Papers › Deep Equilibrium Models

Deep Equilibrium Models

3 Sep 2019NeurIPS 2019 12arXiv:1909.01377archive 2025-07-28

Shaojie Bai, J. Zico Kolter, Vladlen Koltun

We present a new approach to modeling sequential data: the deep equilibrium model (DEQ). Motivated by an observation that the hidden layers of many existing deep sequence models converge towards some fixed point, we propose the DEQ approach that directly finds these equilibrium points via root-finding. Such a method is equivalent to running an infinite depth (weight-tied) feedforward network, but has the notable advantage that we can analytically backpropagate through the equilibrium point using implicit differentiation. Using this approach, training and prediction in these networks require only constant memory, regardless of the effective "depth" of the network. We demonstrate how DEQs can be applied to two state-of-the-art deep sequence models: self-attention transformers and trellis networks. On large-scale language modeling tasks, such as the WikiText-103 benchmark, we show that DEQs 1) often improve performance over these state-of-the-art models (for similar parameter counts); 2) have similar computational requirements to existing models; and 3) vastly reduce memory consumption (often the bottleneck for training large sequence models), demonstrating an up-to 88% memory reduction in our experiments. The code is available at https://github.com/locuslab/deq .

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

No sample from the archive's official repository (locuslab/deq) is linked to this paper; the 12 samples below come from 4 community repositories. Syntology harvested code from locuslab/deq for 3 other papers.

locuslab/deq: Syntology's graph links these samples to Multiscale Deep Equilibrium Models (arXiv:2006.08656; that paper's own run record: 10 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified), Stabilizing Equilibrium Models by Jacobian Regularization (arXiv:2106.14342; that paper's own run record: 0 ran · 3 unverified) and Efficient Training of Deep Equilibrium Models (arXiv:2304.11663; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method.

Syntology 12 code samples harvested from 4 repositories linked to this paper: 9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 12 samples from 4 repositories, 9 ran (7 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 4 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 3 of the 9 samples that ran have no recorded date.

locuslab/deq officialmentioned in papermentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Multiscale Deep Equilibrium Models (arXiv:2006.08656; that paper's own run record: 10 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified), Stabilizing Equilibrium Models by Jacobian Regularization (arXiv:2106.14342; that paper's own run record: 0 ran · 3 unverified) and Efficient Training of Deep Equilibrium Models (arXiv:2304.11663; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
SinclairHudson/DeepEquilibrium mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Multiscale Deep Equilibrium Models (arXiv:2006.08656; that paper's own run record: 10 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
cgoemaere/hamdeq mentioned on GitHubpytorchApache-2.0Syntology: 7 samples, 6 ran (0 instrument-failed) · 1 unverified report
cgoemaere/hopdeq mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
locuslab/impsq mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (2 instrument-failed) · 0 unverified report
locuslab/monotone_op_net mentioned on GitHubpytorchSyntology: not harvested report
lufanma/ifr mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Multiscale Deep Equilibrium Models (arXiv:2006.08656; that paper's own run record: 10 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
martaskrt/qdeq mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
prolearner/hypertorch mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Meta-Learning with Implicit Gradients (arXiv:1909.04630; that paper's own run record: 27 ran (of which 4 constructed an object rather than computing a result; 8 with no instrument failure: 3 honoured, 1 violated, 4 with no contract checked; 19 where Syntology's instrument failed) · 9 unverified); nothing checks that they implement this paper's method. report
reacho/deep-equilibrium-vs-bilevel mentioned on GitHubpytorchMITSyntology: 1 sample, 0 ran · 1 unverified report
sciml/fastdeq.jl mentioned on GitHubMITSyntology: not harvested 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.

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

12 samples harvested: 9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 3 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.

1ran · honoured contract
2ran · our draft was wrong
6ran
3unverified

Licence: 4 of the 12 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 4 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. 1 sample whose link to this paper records no repository is listed under one of this paper's own repositories, because identical code was harvested from it for another 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. 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.

cgoemaere/hamdeq community (archive-listed) 7 samples, 6 ran (0 instrument-failed) · 1 unverified
anderson in 7 papers hopdeq/deq_core/solvers.py ran Apache-2.0 (permissive) · 799e823c70a9d96b · report fixture: signature f:callable/0/?, z_init:Tensor/2/float, iter:int/0/int, m:int/0/int, logger:callable/0/? · returned Tensor · level recorded 2026-09-24
backprop hopdeq/deq_core/backward.py ran Apache-2.0 (permissive) · d9164060df059089 · report fixture: signature grad_output:Tensor/2/float, f:callable/0/?, x:Tensor/2/float, z_free:Tensor/2/float, solver:callable/0/? · returned tuple · level recorded 2026-09-24
damped hopdeq/deq_core/utils/fixed_point_utils.py ran Apache-2.0 (permissive) · 1ec688ed87b414c9 · report fixture: signature f:callable/0/?, beta:float/0/float · returned function · level recorded 2026-09-24
get_function_from_package hopdeq/deq_core/utils/import_utils.py ran Apache-2.0 (permissive) · 06ee28cae377b42a · report fixture: signature package:module/0/?, name:str/0/str, kwargs:NoneType/0/? · returned function · level recorded 2026-09-24
picard hopdeq/deq_core/solvers.py ran Apache-2.0 (permissive) · a0f601462ac10944 · report fixture: signature f:callable/0/?, z_init:Tensor/2/float, iter:int/0/int, logger:callable/0/? · returned Tensor · level recorded 2026-09-24
track_states hopdeq/deq_core/utils/fixed_point_utils.py ran Apache-2.0 (permissive) · 641ed886ac5440c1 · report fixture: signature f:callable/0/?, states:list/1/empty, disable:bool/0/bool · returned function · level recorded 2026-09-24
full_adjoint hopdeq/deq_core/backward.py unverified Apache-2.0 (permissive) · 8b3921143c779266 · report
locuslab/impsq community (archive-listed) 3 samples, 3 ran (2 instrument-failed) · 0 unverified
load_dataset in 276 papers scripts/train_2d_image.py ran · our draft was wrong no licence file found · pointer only · 635c8fdeade67cba · report fixture: signature filename:str/0/str, id:int/0/int · returned dict · level recorded, date not recorded
postprocess in 70 papers
census: 5 implementations from 5 papers, 5 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 4, kind float, dtype float32
scripts/train_2d_image.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 81a8d0038b2d548a · report fixture: signature img_tensor:Tensor/4/float · returned ndarray · level recorded, date not recorded
preprocess in 284 papers
census: 11 implementations from 13 papers, 10 distinct outputs across 5 buckets, one shared input per bucket this sample: bucket 1 of 5, arg 1: rank 2, kind float, dtype float32
scripts/train_2d_image.py ran · honoured contract fingerprinted no licence file found · pointer only · 1194fc2f2f213578 · report fixture: signature img_tensor:Tensor/2/float · returned Tensor · level recorded, date not recorded
martaskrt/qdeq community (archive-listed) 1 sample, 0 ran · 1 unverified
evaluate in 514 papers DEQ-Quantum/train_qdeq.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own unverified licence of this copy not recorded · ee0aeb0dbfe062f7 · report
reacho/deep-equilibrium-vs-bilevel community (archive-listed) 1 sample, 0 ran · 1 unverified
power_iteration_torch_T CelebA/DEQ-vs-bilevel-conv2d.py unverified MIT (permissive) · 20e21defecd44b23 · report

Tasks

Language ModelingLanguage Modelling

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Language Modelling Penn Treebank (Word Level) DEQ-TrellisNet Params 24M #29 of 43 Archive leaderboard report
Language Modelling Penn Treebank (Word Level) DEQ-TrellisNet Test perplexity 57.1 #29 of 43 Archive leaderboard report
Language Modelling WikiText-103 DEQ-Transformer (medium, adaptive embed) Number of params 110M #50 of 89 Archive leaderboard report
Language Modelling WikiText-103 DEQ-Transformer (medium, adaptive embed) Test perplexity 23.2 #50 of 89 Archive leaderboard report
Language Modelling WikiText-103 DEQ-TrellisNet Number of params 180M #66 of 89 Archive leaderboard report
Language Modelling WikiText-103 DEQ-TrellisNet Test perplexity 29.0 #66 of 89 Archive leaderboard report
Language Modelling WikiText-103 DEQ-Transformer (small) Number of params 138M #73 of 89 Archive leaderboard report
Language Modelling WikiText-103 DEQ-Transformer (small) Test perplexity 32.4 #73 of 89 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.

Methods

Introduced by this paper: DEQ

DEQ

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