Papers › Meta-Learning with Implicit Gradients
Meta-Learning with Implicit Gradients
Aravind Rajeswaran, Chelsea Finn, Sham Kakade, Sergey Levine
A core capability of intelligent systems is the ability to quickly learn new tasks by drawing on prior experience. Gradient (or optimization) based meta-learning has recently emerged as an effective approach for few-shot learning. In this formulation, meta-parameters are learned in the outer loop, while task-specific models are learned in the inner-loop, by using only a small amount of data from the current task. A key challenge in scaling these approaches is the need to differentiate through the inner loop learning process, which can impose considerable computational and memory burdens. By drawing upon implicit differentiation, we develop the implicit MAML algorithm, which depends only on the solution to the inner level optimization and not the path taken by the inner loop optimizer. This effectively decouples the meta-gradient computation from the choice of inner loop optimizer. As a result, our approach is agnostic to the choice of inner loop optimizer and can gracefully handle many gradient steps without vanishing gradients or memory constraints. Theoretically, we prove that implicit MAML can compute accurate meta-gradients with a memory footprint that is, up to small constant factors, no more than that which is required to compute a single inner loop gradient and at no overall increase in the total computational cost. Experimentally, we show that these benefits of implicit MAML translate into empirical gains on few-shot image recognition benchmarks.
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="1909.04630")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="1909.04630", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="1909.04630")
Code
Syntology 36 code samples harvested from 6 repositories linked to this paper: 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. Where Syntology's instrument failed: 16 where our contract draft was wrong; 3 where the contract check could not run; failures of Syntology's instrument, not of the code.
By repository: official repository: 7 samples from 1 repository, 7 ran (3 with no instrument failure; 4 where Syntology's instrument failed); community (archive-listed): 29 samples from 5 repositories, 20 ran (5 with no instrument failure; 15 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 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.
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
36 samples harvested: 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. “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: 10 of the 36 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 6 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. 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.
973d52f05dd6e23a · report
fixture: returned Learner · level recorded 2026-09-22 706bb24c4aec6c01 · report
fixture: signature in_channels:int/0/int, out_dim:int/0/int, task:str/0/str, filter_size:int/0/int · returned Sequential · level recorded 2026-09-22 7f3e1e88acd582cb · report
fixture: signature in_dim:int/0/int, out_dim:int/0/int, hidden_sizes:tuple/1/int, float16:bool/0/bool · returned Sequential · level recorded 2026-09-22 census: 8 implementations from 8 papers, 2 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 2, kind float, dtype float32 implicit_maml/learner_model.py ran; the contract check could not run (RAISES) MIT (permissive) ·
b6491973ad8364e5 · report
fixture: returned Tensor · level recorded 2026-09-22 902012dfacde484f · report
fixture: signature x:ndarray/2/float, GPU:bool/0/bool · returned Tensor · level recorded 2026-09-22 census: 24 implementations from 29 papers, 2 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 2, kind float, dtype float32 implicit_maml/learner_model.py ran · honoured contract MIT (permissive) ·
4e11fa374508129f · report
fixture: signature x:Tensor/2/float · returned ndarray · level recorded 2026-09-22 census: 8 implementations from 8 papers, 3 distinct outputs across 3 buckets, one shared input per bucket this sample: bucket 1 of 3, arg 1: rank 2, kind float, dtype float32 implicit_maml/learner_model.py ran · honoured contract MIT (permissive) ·
c5c66678ce4d5e06 · report
fixture: signature x:ndarray/2/float · returned Tensor · level recorded 2026-09-22 ce8a310ec44f2617 · report
fixture: signature params:list/1/Tensor, hparams:list/1/Tensor, K:int/0/int, fp_map:callable/0/?, outer_loss:callable/0/?, tol:float/0/float, set_grad:bool/0/bool, stochastic:bool/0/bool, momentum:float/0/float · returned list · level recorded 2026-09-22 9cf41b1fd2f938db · report
fixture: returned ClipGradNorm · level recorded 2026-09-22 15ad46d31a457fbd · report
fixture: returned IngraphGradientDescent · level recorded 2026-09-22 90253eecd694ad99 · report
fixture: signature original:dict/0/?, replace:dict/0/?, do_not_copy:list/1/SimpleObject · returned dict · level recorded 2026-09-22 ad022c385193f969 · report
fixture: signature model:callable/0/? · returned _GeneratorContextManager · level recorded 2026-09-22 79cbcc7d66c3e96b · report
fixture: signature model:callable/0/?, loss:Tensor/0/float, gradients:NoneType/0/?, parameters:NoneType/0/?, detach:bool/0/bool, learning_rate:float/0/float, allow_unused:bool/0/bool, max_grad_grad_norm:NoneType/0/? · returned SimpleModel · level recorded 2026-09-22 639811fcfbb1e7a8 · report
fixture: signature x:Point/1/int · returned bool · level recorded 2026-09-22 ef358865b0254efe · report
fixture: signature t:dict/0/? · returned generator · level recorded 2026-09-22 eabcf3817110a345 · report
fixture: signature flat:list/1/Tensor, structure:Point/1/list · returned Point · level recorded 2026-09-22 a283594886b8397a · report
fixture: signature params:list/1/Tensor, hparams:list/1/Tensor, K:int/0/int, fp_map:callable/0/?, outer_loss:callable/0/?, tol:float/0/float, set_grad:bool/0/bool, stochastic:bool/0/bool · returned list · level recorded 2026-09-22 2b7ea8d2c1a114db · report
fixture: signature hidden_size:int/0/int, n_classes:int/0/int · returned Sequential · level recorded 2026-09-22 67807e9ca0f086f6 · report
fixture: signature hparams:dict/0/?, params:dict/0/?, optim:callable/0/?, n_steps:int/0/int, log_interval:int/0/int, create_graph:bool/0/bool · returned list · level recorded 2026-09-22 0d5e60bd446341fb · report
fixture: signature params_history:list/1/list, hparams:list/1/Tensor, update_map_history:list/1/callable, outer_loss:callable/0/?, set_grad:bool/0/bool · returned list · level recorded 2026-09-22 729450e798657a96 · report
fixture: signature params:list/1/Tensor, hparams:list/1/Tensor, outer_loss:callable/0/?, set_grad:bool/0/bool · returned tuple · level recorded 2026-09-22 38aac91c527d23aa · report
fixture: signature params:list/1/Tensor, hparams:list/1/Tensor, outer_loss:callable/0/?, K:int/0/int, J_inner:int/0/int, J_outer:int/0/int, fp_map:callable/0/?, inner_loss:NoneType/0/?, linsys_start:list/1/Tensor, stoch_outer:bool/0/bool, stoch_inner:bool/0/bool, optim_build:callable/0/?, opt_params:dict/0/?, set_grad:bool/0/bool, verbose:bool/0/bool · returned tuple · level recorded 2026-09-22 50268c702c3160f7 · report
fixture: returned TaskAsSequenceOfTasks · level recorded 2026-09-22 878503c8b4732592 · report
fixture: signature x:list/1/ndarray, Av:callable/0/?, b:list/1/ndarray · returned float64 · level recorded 2026-09-22 63a920c05cd66bfd · report
fixture: signature x:list/1/ndarray, Av:callable/0/?, b:list/1/ndarray · returned float64 · level recorded 2026-09-22 02e3849d39eb6ee7 · report
fixture: signature Av:callable/0/?, b:list/1/ndarray, x0:list/1/ndarray, num_iterations:int/0/int, debug:bool/0/bool · returned list · level recorded 2026-09-22 7e872f029aaf816a · report
b665a79811957562 · report
ca574f805c91d123 · report
04a97a435d9b70d9 · report
d1abea6ef957cede · report
1248bd4de1408eff · report
fixture: signature params:list/1/Tensor, hparams:list/1/Tensor, K:int/0/int, fp_map:callable/0/?, outer_loss:callable/0/?, tol:float/0/float, set_grad:bool/0/bool, stochastic:bool/0/bool · returned list · level recorded 2026-09-22 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.
6 assemblies on this paper: 6 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).
6 sibling assemblies for implicit MAML (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.
harvested Assembly for implicit MAML (graph method: implicit MAML). 9 bricks; individually on a fixture: 4 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified. The assembly has not been run end-to-end.
one of 6 siblings
- iMAMLMetaLearner entry · level 0 · unverified ·
d1abea6ef957cede - GradBasedMetaLearner helper · level 0 · unverified ·
7e872f029aaf816a - Hvp helper · level 0 · unverified ·
b665a79811957562 - TaskAsSequenceOfTasks helper · level 1 · ran ·
50268c702c3160f7 - grads_on_batch helper · level 0 · unverified ·
04a97a435d9b70d9 - steepest_descent update_rule · level 1 · ran · our draft was wrong ·
02e3849d39eb6ee7 - Task helper · level 0 · unverified ·
ca574f805c91d123 - f1 helper · level 1 · ran · honoured contract ·
878503c8b4732592 - f2 helper · level 1 · ran · our draft was wrong ·
63a920c05cd66bfd
harvested Assembly for implicit MAML (graph method: implicit MAML). 5 bricks; individually on a fixture: 4 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; 3 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.
one of 6 siblings
- fixed_point entry · level 1 · ran · our draft was wrong ·
1248bd4de1408eff - cat_list_to_tensor helper · level 1 · ran · honoured contract ·
3ed1406329714c3f - get_outer_gradients helper · level 1 · ran · our draft was wrong ·
718723909e4de80c - update_tensor_grads helper · level 0 · unverified ·
43e10b662538de12 - grad_unused_zero helper · level 1 · ran · our draft was wrong ·
1b9c1e465ef0029f
harvested Assembly for implicit MAML (graph method: implicit MAML). 12 bricks; individually on a fixture: 8 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.
one of 6 siblings
- GradientCheckpointMAML entry · level 0 · unverified ·
6901e9808bfb8df0 - NaiveMAML helper · level 0 · unverified ·
3c24eaee08990b03 - copy_and_replace helper · level 1 · ran · our draft was wrong ·
90253eecd694ad99 - disable_batchnorm_stats helper · level 1 · ran · our draft was wrong ·
ad022c385193f969 - do_not_copy helper · level 0 · unverified ·
866ceb16f029bf5d - nested_flatten helper · level 1 · ran · our draft was wrong ·
ef358865b0254efe - nested_pack helper · level 1 · ran · our draft was wrong ·
eabcf3817110a345 - IngraphGradientDescent update_rule · level 1 · ran ·
15ad46d31a457fbd - _nested_pack helper · level 0 · unverified ·
7f93a8de5e9255d0 - get_updated_model helper · level 1 · ran · our draft was wrong ·
79cbcc7d66c3e96b - is_namedtuple helper · level 1 · ran · violated contract ·
639811fcfbb1e7a8 - ClipGradNorm helper · level 1 · ran ·
9cf41b1fd2f938db
harvested Assembly for implicit MAML (graph method: implicit MAML). 5 bricks; individually on a fixture: 4 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; 3 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.
one of 6 siblings
- fixed_point entry · level 1 · ran · our draft was wrong ·
ce8a310ec44f2617 - cat_list_to_tensor helper · level 1 · ran · honoured contract ·
3ed1406329714c3f - get_outer_gradients loss · level 1 · ran · our draft was wrong ·
718723909e4de80c - update_tensor_grads update_rule · level 0 · unverified ·
43e10b662538de12 - grad_unused_zero helper · level 1 · ran · our draft was wrong ·
1b9c1e465ef0029f
harvested Assembly for implicit MAML (graph method: implicit MAML). 5 bricks; individually on a fixture: 5 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.
one of 6 siblings
- Learner entry · level 1 · ran ·
973d52f05dd6e23a - to_device helper · level 1 · ran; the contract check could not run (RAISES) ·
902012dfacde484f - to_numpy helper · level 1 · ran · honoured contract ·
4e11fa374508129f - to_tensor helper · level 1 · ran · honoured contract ·
c5c66678ce4d5e06 - to_cuda helper · level 1 · ran; the contract check could not run (RAISES) ·
b6491973ad8364e5
harvested Assembly for implicit MAML (graph method: implicit MAML). 4 bricks; individually on a fixture: 3 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; 3 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.
one of 6 siblings
- stoch_AID entry · level 1 · ran; the contract check could not run (RAISES) ·
38aac91c527d23aa - get_outer_gradients helper · level 1 · ran · our draft was wrong ·
718723909e4de80c - update_tensor_grads helper · level 0 · unverified ·
43e10b662538de12 - grad_unused_zero helper · level 1 · ran · our draft was wrong ·
1b9c1e465ef0029f
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="1909.04630") returns these assemblies with each brick's role and wiring (how to connect).
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Few-Shot Image Classification | Mini-Imagenet 5-way (1-shot) | iMAML HF | Accuracy | 49.30 | #102 of 105 | Archive leaderboard | report |
| Few-Shot Image Classification | OMNIGLOT - 1-Shot, 20-way | iMAML, Hessian-Free | Accuracy | 96.18 | #10 of 20 | Archive leaderboard | report |
| Few-Shot Image Classification | OMNIGLOT - 1-Shot, 5-way | iMAML, Hessian-Free | Accuracy | 99.50 | #6 of 17 | Archive leaderboard | report |
| Few-Shot Image Classification | OMNIGLOT - 5-Shot, 20-way | iMAML, Hessian-Free | Accuracy | 99.14% | #8 of 19 | Archive leaderboard | report |
| Few-Shot Image Classification | OMNIGLOT - 5-Shot, 5-way | iMAML, Hessian-Free | Accuracy | 99.74% | #8 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.
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