Papers › The Missing Invariance Principle Found -- the Reciprocal Twin of Invariant Risk Minimization

The Missing Invariance Principle Found -- the Reciprocal Twin of Invariant Risk Minimization

29 May 2022arXiv:2205.14546archive 2025-07-28

Dongsung Huh, Avinash Baidya

Machine learning models often generalize poorly to out-of-distribution (OOD) data as a result of relying on features that are spuriously correlated with the label during training. Recently, the technique of Invariant Risk Minimization (IRM) was proposed to learn predictors that only use invariant features by conserving the feature-conditioned label expectation 𝔼ₑ[y|f(x)] across environments. However, more recent studies have demonstrated that IRM-v1, a practical version of IRM, can fail in various settings. Here, we identify a fundamental flaw of IRM formulation that causes the failure. We then introduce a complementary notion of invariance, MRI, based on conserving the label-conditioned feature expectation 𝔼ₑ[f(x)|y], which is free of this flaw. Further, we introduce a simplified, practical version of the MRI formulation called MRI-v1. We prove that for general linear problems, MRI-v1 guarantees invariant predictors given sufficient number of environments. We also empirically demonstrate that MRI-v1 strongly out-performs IRM-v1 and consistently achieves near-optimal OOD generalization in image-based nonlinear problems.

PaperPDFCodeCode Syntology ranMethod as code

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: 20 from 1 repository linked to this paper, 1 identical to code harvested from another paper's repository. Across all 21: 13 ran (of which 4 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 0 violated, 7 with no contract checked; 4 where Syntology's instrument failed) · 8 unverified. Where Syntology's instrument failed: 3 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: official repository: 20 samples from 1 repository, 13 ran (9 with no instrument failure; 4 where Syntology's instrument failed); 1 identical to code first harvested elsewhere. 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 between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 2 of the 13 samples that ran have no recorded date.

ibm/mri officialmentioned in papermentioned on GitHubpytorchSyntology: 20 samples, 13 ran (4 instrument-failed) · 7 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: 13 ran (of which 4 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 0 violated, 7 with no contract checked; 4 where Syntology's instrument failed) · 8 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.

2ran · honoured contract
3ran · our draft was wrong
1ran; the contract check could not run
7ran
8unverified

Licence: 1 of the 21 samples is 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 ibm/mri. 1 sample is listed last, in a group without a repository. “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”. For 1 sample that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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.

ibm/mri official repository 20 samples, 13 ran (4 instrument-failed) · 7 unverified
Algorithm in 26 papers custom_algorithms.py ran MIT (permissive) · 60d5898728b2ef53 · report fixture: returned Algorithm · level recorded 2026-09-22
Classifier in 72 papers custom_algorithms.py ran · our draft was wrong MIT (permissive) · 1389f95d1fb9f67e · report fixture: signature in_features:int/0/int, out_features:int/0/int, hparams:dict/0/? · returned Sequential · level recorded 2026-09-22
Identity in 49 papers
census: 10 implementations from 13 papers, 4 distinct outputs across 4 buckets, one shared input per bucket
custom_algorithms.py ran fingerprinted MIT (permissive) · f0e9d2dc26748363 · report fixture: returned Identity · level recorded 2026-09-22
LeNet5 custom_algorithms.py ran MIT (permissive) · 1a73afa879cb603b · report fixture: returned LeNet5 · level recorded 2026-09-22
ST_ConvNet custom_algorithms.py ran MIT (permissive) · ff54592da5080e3a · report fixture: returned ST_ConvNet · level recorded 2026-09-22
complex2real custom_algorithms.py ran MIT (permissive) · 79dcc6f470520bde · report fixture: signature x:Tensor/2/complex · returned Tensor · level recorded 2026-09-24
complexify custom_algorithms.py ran fingerprinted MIT (permissive) · 9821d3e2333fe81b · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-24
get_grad_norm in 45 papers custom_algorithms.py ran · honoured contract MIT (permissive) · 0c216d63456de1ec · report fixture: signature params:list/1/Tensor · returned Tensor · level recorded 2026-09-22
get_loss_fn in 12 papers domainbed/algorithms.py ran · our draft was wrong MIT (permissive) · 79a63acaa13df2ea · report fixture: signature hparams:dict/0/? · returned CrossEntropyLoss · level recorded, date not recorded
get_optimizer in 228 papers domainbed/algorithms.py ran · our draft was wrong MIT (permissive) · f98e24eb0d2d32cf · report fixture: signature hparams:dict/0/?, parameters:generator/0/? · returned SGD · level recorded, date not recorded
get_weight_norm custom_algorithms.py ran · honoured contract MIT (permissive) · c6faf56a6ad7ccbc · report fixture: signature params:list/1/Tensor · returned Tensor · level recorded 2026-09-22
output_modification custom_algorithms.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · 23db9d78066152ca · report fixture: signature logits:Tensor/3/float, label:Tensor/3/float, loss_type:str/0/str, num_classes:int/0/int · returned tuple · level recorded 2026-09-22
real2complex custom_algorithms.py ran fingerprinted MIT (permissive) · 6a052df58baa9181 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-24
ERM in 13 papers custom_algorithms.py unverified MIT (permissive) · 5aebea4d4ebff0d4 · report
Featurizer in 11 papers custom_algorithms.py unverified MIT (permissive) · 28f76c5b44ed54e5 · report
IRM custom_algorithms.py unverified MIT (permissive) · d374678281d0659c · report
MRI custom_algorithms.py unverified MIT (permissive) · 15b92d3235dcbfd7 · report
ResNet in 139 papers custom_algorithms.py unverified MIT (permissive) · f795ad5cd9b0e0fe · report
get_Featurizer_dict custom_algorithms.py unverified MIT (permissive) · dde6698ef323ba28 · report
get_network in 100 papers custom_algorithms.py unverified MIT (permissive) · 90ee0fb395848111 · report
Repository not located 1 sample, 0 ran · 1 unverified
1 sample is identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
get_algorithm_class in 42 papers repository not located unverified licence of this copy not recorded · b0bc80b1655a6802 · 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.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for MRI (graph method: MRI). 25 bricks; individually on a fixture: 18 ran (of which 8 constructed an object rather than computing a result; 13 with no instrument failure: 2 honoured, 0 violated, 11 with no contract checked; 5 where Syntology's instrument failed) · 7 unverified. The assembly has not been run end-to-end.

  1. MRI entry · level 0 · unverified · 15b92d3235dcbfd7
  2. IRM model · level 0 · unverified · d374678281d0659c
  3. ERM helper · level 0 · unverified · 5aebea4d4ebff0d4
  4. get_grad_norm helper · level 1 · ran · honoured contract · 0c216d63456de1ec
  5. get_optimizer helper · level 1 · ran · our draft was wrong · f98e24eb0d2d32cf
  6. get_weight_norm helper · level 1 · ran · honoured contract · c6faf56a6ad7ccbc
  7. output_modification helper · level 1 · ran; the contract check could not run (RAISES) · 23db9d78066152ca
  8. Algorithm helper · level 1 · ran · 60d5898728b2ef53
  9. get_network helper · level 0 · unverified · 90ee0fb395848111
  10. get_loss_fn helper · level 1 · ran · our draft was wrong · 79a63acaa13df2ea
  11. Classifier helper · level 1 · ran · our draft was wrong · 1389f95d1fb9f67e
  12. Featurizer helper · level 0 · unverified · 28f76c5b44ed54e5
  13. Identity helper · level 1 · ran · f0e9d2dc26748363
  14. complexify helper · level 1 · ran · 9821d3e2333fe81b
  15. get_Featurizer_dict helper · level 0 · unverified · dde6698ef323ba28
  16. LeNet5 helper · level 1 · ran · 1a73afa879cb603b
  17. MLP helper · level 1 · ran · bacc92fd6ae22e2c
  18. MNIST_CNN helper · level 1 · ran · e1494c5ebd38c29b
  19. ResNet helper · level 0 · unverified · f795ad5cd9b0e0fe
  20. ST_ConvNet helper · level 1 · ran · ff54592da5080e3a
  21. Wide_ResNet helper · level 1 · ran · 6a63af402870932f
  22. conv3x3 helper · level 1 · ran · our draft was wrong · 00e569acd6b45ef0
  23. wide_basic helper · level 1 · ran · a47120fe8df1b363
  24. complex2real helper · level 1 · ran · 79dcc6f470520bde
  25. real2complex helper · level 1 · ran · 6a052df58baa9181

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="2205.14546") returns these assemblies with each brick's role and wiring (how to connect).

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